
memory-optimization
Graph-backed memory and context optimization workflows with graphify first and document conversion helpers second.
- version
- 0.6.3
- GitHub stars
- 9
Install
/plugin install memory-optimization@agent-powerupsRun it inside Claude Code after adding the marketplace with /plugin marketplace add yeaight7/agent-powerups.
Contents
Discovered from sourceSkills 8
Defuddle
Purpose
Extract readable Markdown from ordinary web pages by stripping navigation, ads, and page chrome.
When to Use
- User provides a documentation page, article, or blog post URL.
- Clean Markdown extraction is preferable to noisy HTML.
- Web page clutter would waste context.
Do not use when:
- URL already points to Markdown.
- Response is an API payload.
- Page requires authentication the tool cannot satisfy.
Requirements
Required tool:
- Defuddle CLI
Check:
Get-Command defuddle -ErrorAction SilentlyContinue
defuddle --version
Install:
npm install -g defuddle
Rules:
- Do not assume Defuddle is installed.
- Do not auto-install without user approval.
- Show the install command before running it.
Inputs
- URL to parse
Workflow
- Check whether Defuddle CLI is available.
- If missing, tell the user before attempting extraction.
- Prefer Markdown output:
defuddle parse <url> --md
- Save to a file when needed:
defuddle parse <url> --md -o content.md
- For metadata-only needs, query a specific property:
defuddle parse <url> -p title
defuddle parse <url> -p description
defuddle parse <url> -p domain
Output
- Clean Markdown content
- Optional metadata fields
Verification
- Defuddle availability was checked first
- No extraction was claimed if the tool was missing
- Output is the article or documentation body, not page chrome
Failure Modes
- Page blocks automated access
- JavaScript-heavy page renders poorly
- Auth-gated content is inaccessible
Missing Dependency Behavior
If Defuddle is missing:
- Say extraction did not happen.
- Tell the user Defuddle CLI is required.
- Ask before installing it.
- Show the install command.
- Fall back to another web-reading method.
/graphify
Turn any folder of files into a navigable knowledge graph with community detection, an honest audit trail, and three outputs: interactive HTML, GraphRAG-ready JSON, and a plain-language GRAPH_REPORT.md.
Upstream
- Upstream project:
https://github.com/safishamsi/graphify - Official PyPI package:
graphifyy(doubley) - Upstream license: MIT
- This repo ships guidance for using the upstream tool. It does not vendor the Python package itself.
Read UPSTREAM.md before changing compatibility, install, or license claims.
Requirements
Required tools:
- Python 3.10+
- Official
graphifyypackage installed for thepythoninterpreter this skill will use
Check:
Get-Command graphify -ErrorAction SilentlyContinue
python -c "import graphify, sys; print(sys.executable)" 2>$null
Install options:
uv tool install graphifyy
pipx install graphifyy
python -m pip install graphifyy
Rules:
- Do not assume
graphifyyis installed. - Do not auto-install without user approval.
- Show the install command before running it.
- If
graphifyexists on PATH butpython -c "import graphify"fails, stop and tell the user the skill cannot use that interpreter yet.
Manual CLI Notes
- In PowerShell, run
graphify ., not/graphify .. - To install upstream Codex integration after the package is present:
graphify codex install - Manual CLI use and skill-guided use are separate: the package must exist first in both cases.
Usage
/graphify # full pipeline on current directory → Obsidian vault
/graphify <path> # full pipeline on specific path
/graphify <path> --mode deep # thorough extraction, richer INFERRED edges
/graphify <path> --update # incremental - re-extract only new/changed files
/graphify <path> --directed # build directed graph (preserves edge direction: source→target)
/graphify <path> --whisper-model medium # use a larger Whisper model for better transcription accuracy
/graphify <path> --cluster-only # rerun clustering on existing graph
/graphify <path> --no-viz # skip visualization, just report + JSON
/graphify <path> --html # (HTML is generated by default - this flag is a no-op)
/graphify <path> --svg # also export graph.svg (embeds in Notion, GitHub)
/graphify <path> --graphml # export graph.graphml (Gephi, yEd)
/graphify <path> --neo4j # generate graphify-out/cypher.txt for Neo4j
/graphify <path> --neo4j-push bolt://localhost:7687 # push directly to Neo4j
/graphify <path> --wiki # build agent-crawlable wiki (index.md + one article per community)
/graphify <path> --obsidian # generate Obsidian vault
/graphify <path> --obsidian --obsidian-dir ~/my/vault # write vault to custom path (e.g. existing vault)
/graphify <path> --mcp # start MCP stdio server for agent access
/graphify <path> --watch # watch folder, auto-rebuild on code changes (no LLM needed)
/graphify add <url> # fetch URL, save to ./raw, update graph
/graphify add <url> --author "Name" # tag who wrote it
/graphify add <url> --contributor "Name" # tag who added it to the corpus
/graphify query "<question>" # BFS traversal - broad context
/graphify query "<question>" --dfs # DFS - trace a specific path
/graphify query "<question>" --budget 1500 # cap answer at N tokens
/graphify path "AuthModule" "Database" # shortest path between two concepts
/graphify explain "SwinTransformer" # plain-language explanation of a node
What graphify is for
graphify is built around Andrej Karpathy's /raw folder workflow: drop anything into a folder - papers, tweets, screenshots, code, notes - and get a structured knowledge graph that shows you what you didn't know was connected.
Three things it does that your AI assistant alone cannot:
- Persistent graph - relationships are stored in
graphify-out/graph.jsonand survive across sessions. Ask questions weeks later without re-reading everything. - Honest audit trail - every edge is tagged EXTRACTED, INFERRED, or AMBIGUOUS. You know what was found vs invented.
- Cross-document surprise - community detection finds connections between concepts in different files that you would never think to ask about directly.
Use it for:
- A codebase you're new to (understand architecture before touching anything)
- A reading list (papers + tweets + notes → one navigable graph)
- A research corpus (citation graph + concept graph in one)
- Your personal /raw folder (drop everything in, let it grow, query it)
What You Must Do When Invoked
If no path was given, use . (current directory). Do not ask the user for a path.
Follow these steps in order. Do not skip steps.
Step 1 - Ensure graphify is installed
# Check CLI presence and Python importability
Get-Command graphify -ErrorAction SilentlyContinue
python -c "import graphify, sys; open('.graphify_python', 'w').write(sys.executable)" 2>$null
If the import succeeds, print nothing and move straight to Step 2.
If it fails:
- Stop. Do not continue with detection or extraction.
- Tell the user
graphifyyis required and is not currently importable frompython. - Show install options:
uv tool install graphifyy
pipx install graphifyy
python -m pip install graphifyy
- Ask before installing it.
Step 2 - Detect files
python -c "
import json
from graphify.detect import detect
from pathlib import Path
result = detect(Path('INPUT_PATH'))
print(json.dumps(result))
" > .graphify_detect.json
Replace INPUT_PATH with the actual path the user provided. Do NOT cat or print the JSON - read it silently and present a clean summary instead:
Corpus: X files · ~Y words
code: N files (.py .ts .go ...)
docs: N files (.md .txt ...)
papers: N files (.pdf ...)
images: N files
video: N files (.mp4 .mp3 ...)
Omit any category with 0 files from the summary.
Then act on it:
- If
total_filesis 0: stop with "No supported files found in [path]." - If
skipped_sensitiveis non-empty: mention file count skipped, not the file names. - If
total_words> 2,000,000 ORtotal_files> 200: show the warning and the top 5 subdirectories by file count, then ask which subfolder to run on. Wait for the user's answer before proceeding. - Otherwise: proceed directly to Step 2.5 if video files were detected, or Step 3 if not.
Step 2.5 - Transcribe video / audio files (only if video files detected)
Skip this step entirely if detect returned zero video files.
Video and audio files cannot be read directly. Transcribe them to text first, then treat the transcripts as doc files in Step 3.
Strategy: Read the god nodes from the detect output or analysis file. You are already a language model - write a one-sentence domain hint yourself from those labels. Then pass it to Whisper as the initial prompt. No separate API call needed.
However, if the corpus has only video files and no other docs/code, use the generic fallback prompt: "Use proper punctuation and paragraph breaks."
Step 1 - Write the Whisper prompt yourself.
Read the top god node labels from detect output or analysis, then compose a short domain hint sentence, for example:
- Labels:
transformer, attention, encoder, decoder->"Machine learning research on transformer architectures and attention mechanisms. Use proper punctuation and paragraph breaks." - Labels:
kubernetes, deployment, pod, helm->"DevOps discussion about Kubernetes deployments and Helm charts. Use proper punctuation and paragraph breaks."
Set it as $env:GRAPHIFY_WHISPER_PROMPT before running the transcription command.
Step 2 - Transcribe (PowerShell):
& (Get-Content graphify-out\.graphify_python) -c "
import json, os
from pathlib import Path
from graphify.transcribe import transcribe_all
detect = json.loads(Path('graphify-out/.graphify_detect.json').read_text())
video_files = detect.get('files', {}).get('video', [])
prompt = os.environ.get('GRAPHIFY_WHISPER_PROMPT', 'Use proper punctuation and paragraph breaks.')
transcript_paths = transcribe_all(video_files, initial_prompt=prompt)
print(json.dumps(transcript_paths))
" | Out-File -FilePath graphify-out\.graphify_transcripts.json -Encoding utf8
After transcription:
- Read the transcript paths from
graphify-out\.graphify_transcripts.json - Add them to the docs list before dispatching semantic subagents in Step 3B
- Print how many transcripts were created:
Transcribed N video file(s) -> treating as docs - If transcription fails for a file, print a warning and continue with the rest
Whisper model: Default is base. If the user passed --whisper-model <name>, set $env:GRAPHIFY_WHISPER_MODEL = "<name>" before running the command above.
Step 3 - Extract entities and relationships
Before starting: note whether --mode deep was given. You must pass DEEP_MODE=true to every subagent in Step B2 if it was. Track this from the original invocation - do not lose it.
This step has two parts: structural extraction (deterministic, free) and semantic extraction (your AI model, costs tokens).
Run Part A (AST) and Part B (semantic) in parallel. Dispatch all semantic subagents AND start AST extraction in the same message. Both can run simultaneously since they operate on different file types. Merge results in Part C as before.
Note: Parallelizing AST + semantic saves 5-15s on large corpora. AST is deterministic and fast; start it while subagents are processing docs/papers.
Part A - Structural extraction for code files
For any code files detected, run AST extraction in parallel with Part B subagents:
python -c "
import sys, json
from graphify.extract import collect_files, extract
from pathlib import Path
import json
code_files = []
detect = json.loads(Path('.graphify_detect.json').read_text())
for f in detect.get('files', {}).get('code', []):
code_files.extend(collect_files(Path(f)) if Path(f).is_dir() else [Path(f)])
if code_files:
result = extract(code_files)
Path('.graphify_ast.json').write_text(json.dumps(result, indent=2))
print(f'AST: {len(result[\"nodes\"])} nodes, {len(result[\"edges\"])} edges')
else:
Path('.graphify_ast.json').write_text(json.dumps({'nodes':[],'edges':[],'input_tokens':0,'output_tokens':0}))
print('No code files - skipping AST extraction')
"
Part B - Semantic extraction (parallel subagents)
Fast path: If detection found zero docs, papers, and images (code-only corpus), skip Part B entirely and go straight to Part C. AST handles code - there is nothing for semantic subagents to do.
MANDATORY: You MUST use the Agent tool here. Reading files yourself one-by-one is forbidden - it is 5-10x slower. If you do not use the Agent tool you are doing this wrong.
Before dispatching subagents, print a timing estimate:
- Load
total_wordsand file counts from.graphify_detect.json - Estimate agents needed:
ceil(uncached_non_code_files / 22)(chunk size is 20-25) - Estimate time: ~45s per agent batch (they run in parallel, so total ≈ 45s × ceil(agents/parallel_limit))
- Print: "Semantic extraction: ~N files → X agents, estimated ~Ys"
Step B0 - Check extraction cache first
Before dispatching any subagents, check which files already have cached extraction results:
python -c "
import json
from graphify.cache import check_semantic_cache
from pathlib import Path
detect = json.loads(Path('.graphify_detect.json').read_text())
all_files = [f for files in detect['files'].values() for f in files]
cached_nodes, cached_edges, cached_hyperedges, uncached = check_semantic_cache(all_files)
if cached_nodes or cached_edges or cached_hyperedges:
Path('.graphify_cached.json').write_text(json.dumps({'nodes': cached_nodes, 'edges': cached_edges, 'hyperedges': cached_hyperedges}))
Path('.graphify_uncached.txt').write_text('\n'.join(uncached))
print(f'Cache: {len(all_files)-len(uncached)} files hit, {len(uncached)} files need extraction')
"
Only dispatch subagents for files listed in .graphify_uncached.txt. If all files are cached, skip to Part C directly.
Step B1 - Split into chunks
Load files from .graphify_uncached.txt. Split into chunks of 20-25 files each. Each image gets its own chunk (vision needs separate context).
Step B2 - Dispatch ALL subagents in a single message
Call the Agent tool multiple times IN THE SAME RESPONSE - one call per chunk. This is the only way they run in parallel. If you make one Agent call, wait, then make another, you are doing it sequentially and defeating the purpose.
Concrete example for 3 chunks:
[Agent tool call 1: files 1-15]
[Agent tool call 2: files 16-30]
[Agent tool call 3: files 31-45]
All three in one message. Not three separate messages.
Each subagent receives this exact prompt (substitute FILE_LIST, CHUNK_NUM, TOTAL_CHUNKS, and DEEP_MODE):
You are a graphify extraction subagent. Read the files listed and extract a knowledge graph fragment.
Output ONLY valid JSON matching the schema below - no explanation, no markdown fences, no preamble.
Files (chunk CHUNK_NUM of TOTAL_CHUNKS):
FILE_LIST
Rules:
- EXTRACTED: relationship explicit in source (import, call, citation, "see §3.2")
- INFERRED: reasonable inference (shared data structure, implied dependency)
- AMBIGUOUS: uncertain - flag for review, do not omit
Code files: focus on semantic edges AST cannot find (call relationships, shared data, arch patterns).
Do not re-extract imports - AST already has those.
Doc/paper files: extract named concepts, entities, citations. Also extract rationale — sections that explain WHY a decision was made, trade-offs chosen, or design intent. These become nodes with `rationale_for` edges pointing to the concept they explain.
Image files: use vision to understand what the image IS - do not just OCR.
UI screenshot: layout patterns, design decisions, key elements, purpose.
Chart: metric, trend/insight, data source.
Tweet/post: claim as node, author, concepts mentioned.
Diagram: components and connections.
Research figure: what it demonstrates, method, result.
Handwritten/whiteboard: ideas and arrows, mark uncertain readings AMBIGUOUS.
DEEP_MODE (if --mode deep was given): be aggressive with INFERRED edges - indirect deps,
shared assumptions, latent couplings. Mark uncertain ones AMBIGUOUS instead of omitting.
Semantic similarity: if two concepts in this chunk solve the same problem or represent the same idea without any structural link (no import, no call, no citation), add a `semantically_similar_to` edge marked INFERRED with a confidence_score reflecting how similar they are (0.6-0.95). Examples:
- Two functions that both validate user input but never call each other
- A class in code and a concept in a paper that describe the same algorithm
- Two error types that handle the same failure mode differently
Only add these when the similarity is genuinely non-obvious and cross-cutting. Do not add them for trivially similar things.
Hyperedges: if 3 or more nodes clearly participate together in a shared concept, flow, or pattern that is not captured by pairwise edges alone, add a hyperedge to a top-level `hyperedges` array. Examples:
- All classes that implement a common protocol or interface
- All functions in an authentication flow (even if they don't all call each other)
- All concepts from a paper section that form one coherent idea
Use sparingly — only when the group relationship adds information beyond the pairwise edges. Maximum 3 hyperedges per chunk.
If a file has YAML frontmatter (--- ... ---), copy source_url, captured_at, author,
contributor onto every node from that file.
confidence_score is REQUIRED on every edge - never omit it, never use 0.5 as a default:
- EXTRACTED edges: confidence_score = 1.0 always
- INFERRED edges: reason about each edge individually.
Direct structural evidence (shared data structure, clear dependency): 0.8-0.9.
Reasonable inference with some uncertainty: 0.6-0.7.
Weak or speculative: 0.4-0.5. Most edges should be 0.6-0.9, not 0.5.
- AMBIGUOUS edges: 0.1-0.3
Output exactly this JSON (no other text):
{"nodes":[{"id":"filestem_entityname","label":"Human Readable Name","file_type":"code|document|paper|image","source_file":"relative/path","source_location":null,"source_url":null,"captured_at":null,"author":null,"contributor":null}],"edges":[{"source":"node_id","target":"node_id","relation":"calls|implements|references|cites|conceptually_related_to|shares_data_with|semantically_similar_to|rationale_for","confidence":"EXTRACTED|INFERRED|AMBIGUOUS","confidence_score":1.0,"source_file":"relative/path","source_location":null,"weight":1.0}],"hyperedges":[{"id":"snake_case_id","label":"Human Readable Label","nodes":["node_id1","node_id2","node_id3"],"relation":"participate_in|implement|form","confidence":"EXTRACTED|INFERRED","confidence_score":0.75,"source_file":"relative/path"}],"input_tokens":0,"output_tokens":0}
Step B3 - Collect, cache, and merge
Wait for all subagents. For each result:
- Check that
graphify-out/.graphify_chunk_NN.jsonexists on disk — this is the success signal - If the file exists and contains valid JSON with
nodesandedges, include it and save to cache - If the file is missing, the subagent was likely dispatched as read-only (Explore type) — print a warning: "chunk N missing from disk — subagent may have been read-only. Re-run with general-purpose agent." Do not silently skip.
- If a subagent failed or returned invalid JSON, print a warning and skip that chunk - do not abort
If more than half the chunks failed or are missing, stop and tell the user to re-run and ensure subagent_type="general-purpose" is used.
Save new results to cache:
python -c "
import json
from graphify.cache import save_semantic_cache
from pathlib import Path
new = json.loads(Path('.graphify_semantic_new.json').read_text()) if Path('.graphify_semantic_new.json').exists() else {'nodes':[],'edges':[],'hyperedges':[]}
saved = save_semantic_cache(new.get('nodes', []), new.get('edges', []), new.get('hyperedges', []))
print(f'Cached {saved} files')
"
Merge cached + new results into .graphify_semantic.json:
python -c "
import json
from pathlib import Path
cached = json.loads(Path('.graphify_cached.json').read_text()) if Path('.graphify_cached.json').exists() else {'nodes':[],'edges':[],'hyperedges':[]}
new = json.loads(Path('.graphify_semantic_new.json').read_text()) if Path('.graphify_semantic_new.json').exists() else {'nodes':[],'edges':[],'hyperedges':[]}
all_nodes = cached['nodes'] + new.get('nodes', [])
all_edges = cached['edges'] + new.get('edges', [])
all_hyperedges = cached.get('hyperedges', []) + new.get('hyperedges', [])
seen = set()
deduped = []
for n in all_nodes:
if n['id'] not in seen:
seen.add(n['id'])
deduped.append(n)
merged = {
'nodes': deduped,
'edges': all_edges,
'hyperedges': all_hyperedges,
'input_tokens': new.get('input_tokens', 0),
'output_tokens': new.get('output_tokens', 0),
}
Path('.graphify_semantic.json').write_text(json.dumps(merged, indent=2))
print(f'Extraction complete - {len(deduped)} nodes, {len(all_edges)} edges ({len(cached[\"nodes\"])} from cache, {len(new.get(\"nodes\",[]))} new)')
"
Clean up temp files: Remove-Item -ErrorAction SilentlyContinue .graphify_cached.json, .graphify_uncached.txt, .graphify_semantic_new.json
Part C - Merge AST + semantic into final extraction
python -c "
import sys, json
from pathlib import Path
ast = json.loads(Path('.graphify_ast.json').read_text())
sem = json.loads(Path('.graphify_semantic.json').read_text())
# Merge: AST nodes first, semantic nodes deduplicated by id
seen = {n['id'] for n in ast['nodes']}
merged_nodes = list(ast['nodes'])
for n in sem['nodes']:
if n['id'] not in seen:
merged_nodes.append(n)
seen.add(n['id'])
merged_edges = ast['edges'] + sem['edges']
merged_hyperedges = sem.get('hyperedges', [])
merged = {
'nodes': merged_nodes,
'edges': merged_edges,
'hyperedges': merged_hyperedges,
'input_tokens': sem.get('input_tokens', 0),
'output_tokens': sem.get('output_tokens', 0),
}
Path('.graphify_extract.json').write_text(json.dumps(merged, indent=2))
total = len(merged_nodes)
edges = len(merged_edges)
print(f'Merged: {total} nodes, {edges} edges ({len(ast[\"nodes\"])} AST + {len(sem[\"nodes\"])} semantic)')
"
Step 4 - Build graph, cluster, analyze, generate outputs
New-Item -ItemType Directory -Force -Path graphify-out | Out-Null
python -c "
import sys, json
from graphify.build import build_from_json
from graphify.cluster import cluster, score_all
from graphify.analyze import god_nodes, surprising_connections, suggest_questions
from graphify.report import generate
from graphify.export import to_json
from pathlib import Path
extraction = json.loads(Path('.graphify_extract.json').read_text())
detection = json.loads(Path('.graphify_detect.json').read_text())
G = build_from_json(extraction)
communities = cluster(G)
cohesion = score_all(G, communities)
tokens = {'input': extraction.get('input_tokens', 0), 'output': extraction.get('output_tokens', 0)}
gods = god_nodes(G)
surprises = surprising_connections(G, communities)
labels = {cid: 'Community ' + str(cid) for cid in communities}
# Placeholder questions - regenerated with real labels in Step 5
questions = suggest_questions(G, communities, labels)
report = generate(G, communities, cohesion, labels, gods, surprises, detection, tokens, 'INPUT_PATH', suggested_questions=questions)
Path('graphify-out/GRAPH_REPORT.md').write_text(report)
to_json(G, communities, 'graphify-out/graph.json')
analysis = {
'communities': {str(k): v for k, v in communities.items()},
'cohesion': {str(k): v for k, v in cohesion.items()},
'gods': gods,
'surprises': surprises,
'questions': questions,
}
Path('.graphify_analysis.json').write_text(json.dumps(analysis, indent=2))
if G.number_of_nodes() == 0:
print('ERROR: Graph is empty - extraction produced no nodes.')
print('Possible causes: all files were skipped, binary-only corpus, or extraction failed.')
raise SystemExit(1)
print(f'Graph: {G.number_of_nodes()} nodes, {G.number_of_edges()} edges, {len(communities)} communities')
"
If this step prints ERROR: Graph is empty, stop and tell the user what happened - do not proceed to labeling or visualization.
Replace INPUT_PATH with the actual path.
Step 5 - Label communities
Read .graphify_analysis.json. For each community key, look at its node labels and write a 2-5 word plain-language name (e.g. "Attention Mechanism", "Training Pipeline", "Data Loading").
Then regenerate the report and save the labels for the visualizer:
python -c "
import sys, json
from graphify.build import build_from_json
from graphify.cluster import score_all
from graphify.analyze import god_nodes, surprising_connections, suggest_questions
from graphify.report import generate
from pathlib import Path
extraction = json.loads(Path('.graphify_extract.json').read_text())
detection = json.loads(Path('.graphify_detect.json').read_text())
analysis = json.loads(Path('.graphify_analysis.json').read_text())
G = build_from_json(extraction)
communities = {int(k): v for k, v in analysis['communities'].items()}
cohesion = {int(k): v for k, v in analysis['cohesion'].items()}
tokens = {'input': extraction.get('input_tokens', 0), 'output': extraction.get('output_tokens', 0)}
# LABELS - replace these with the names you chose above
labels = LABELS_DICT
# Regenerate questions with real community labels (labels affect question phrasing)
questions = suggest_questions(G, communities, labels)
report = generate(G, communities, cohesion, labels, analysis['gods'], analysis['surprises'], detection, tokens, 'INPUT_PATH', suggested_questions=questions)
Path('graphify-out/GRAPH_REPORT.md').write_text(report)
Path('.graphify_labels.json').write_text(json.dumps({str(k): v for k, v in labels.items()}))
print('Report updated with community labels')
"
Replace LABELS_DICT with the actual dict you constructed (e.g. {0: "Attention Mechanism", 1: "Training Pipeline"}).
Replace INPUT_PATH with the actual path.
Step 6 - Generate Obsidian vault (opt-in) + HTML
Generate HTML always (unless --no-viz). Obsidian vault only if --obsidian was explicitly given — skip it otherwise, it generates one file per node.
If --obsidian was given:
- If
--obsidian-dir <path>was also given, use that path as the vault directory. Otherwise default tographify-out/obsidian.
python -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_obsidian, to_canvas
from pathlib import Path
extraction = json.loads(Path('.graphify_extract.json').read_text())
analysis = json.loads(Path('.graphify_analysis.json').read_text())
labels_raw = json.loads(Path('.graphify_labels.json').read_text()) if Path('.graphify_labels.json').exists() else {}
G = build_from_json(extraction)
communities = {int(k): v for k, v in analysis['communities'].items()}
cohesion = {int(k): v for k, v in analysis['cohesion'].items()}
labels = {int(k): v for k, v in labels_raw.items()}
obsidian_dir = 'OBSIDIAN_DIR' # replace with --obsidian-dir value, or 'graphify-out/obsidian' if not given
n = to_obsidian(G, communities, obsidian_dir, community_labels=labels or None, cohesion=cohesion)
print(f'Obsidian vault: {n} notes in {obsidian_dir}/')
to_canvas(G, communities, f'{obsidian_dir}/graph.canvas', community_labels=labels or None)
print(f'Canvas: {obsidian_dir}/graph.canvas - open in Obsidian for structured community layout')
print()
print(f'Open {obsidian_dir}/ as a vault in Obsidian.')
print(' Graph view - nodes colored by community (set automatically)')
print(' graph.canvas - structured layout with communities as groups')
print(' _COMMUNITY_* - overview notes with cohesion scores and dataview queries')
"
Generate the HTML graph (always, unless --no-viz):
python -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_html
from pathlib import Path
extraction = json.loads(Path('.graphify_extract.json').read_text())
analysis = json.loads(Path('.graphify_analysis.json').read_text())
labels_raw = json.loads(Path('.graphify_labels.json').read_text()) if Path('.graphify_labels.json').exists() else {}
G = build_from_json(extraction)
communities = {int(k): v for k, v in analysis['communities'].items()}
labels = {int(k): v for k, v in labels_raw.items()}
if G.number_of_nodes() > 5000:
print(f'Graph has {G.number_of_nodes()} nodes - too large for HTML viz. Use Obsidian vault instead.')
else:
to_html(G, communities, 'graphify-out/graph.html', community_labels=labels or None)
print('graph.html written - open in any browser, no server needed')
"
Step 7 - Neo4j export (only if --neo4j or --neo4j-push flag)
If --neo4j - generate a Cypher file for manual import:
python -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_cypher
from pathlib import Path
G = build_from_json(json.loads(Path('.graphify_extract.json').read_text()))
to_cypher(G, 'graphify-out/cypher.txt')
print('cypher.txt written - import with: cypher-shell < graphify-out/cypher.txt')
"
If --neo4j-push <uri> - push directly to a running Neo4j instance. Ask the user for credentials if not provided:
python -c "
import sys, json
from graphify.build import build_from_json
from graphify.cluster import cluster
from graphify.export import push_to_neo4j
from pathlib import Path
extraction = json.loads(Path('.graphify_extract.json').read_text())
analysis = json.loads(Path('.graphify_analysis.json').read_text())
G = build_from_json(extraction)
communities = {int(k): v for k, v in analysis['communities'].items()}
result = push_to_neo4j(G, uri='NEO4J_URI', user='NEO4J_USER', password='NEO4J_PASSWORD', communities=communities)
print(f'Pushed to Neo4j: {result[\"nodes\"]} nodes, {result[\"edges\"]} edges')
"
Replace NEO4J_URI, NEO4J_USER, NEO4J_PASSWORD with actual values. Default URI is bolt://localhost:7687, default user is neo4j. Uses MERGE - safe to re-run without creating duplicates.
Step 7b - SVG export (only if --svg flag)
python -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_svg
from pathlib import Path
extraction = json.loads(Path('.graphify_extract.json').read_text())
analysis = json.loads(Path('.graphify_analysis.json').read_text())
labels_raw = json.loads(Path('.graphify_labels.json').read_text()) if Path('.graphify_labels.json').exists() else {}
G = build_from_json(extraction)
communities = {int(k): v for k, v in analysis['communities'].items()}
labels = {int(k): v for k, v in labels_raw.items()}
to_svg(G, communities, 'graphify-out/graph.svg', community_labels=labels or None)
print('graph.svg written - embeds in Obsidian, Notion, GitHub READMEs')
"
Step 7c - GraphML export (only if --graphml flag)
python -c "
import json
from graphify.build import build_from_json
from graphify.export import to_graphml
from pathlib import Path
extraction = json.loads(Path('.graphify_extract.json').read_text())
analysis = json.loads(Path('.graphify_analysis.json').read_text())
G = build_from_json(extraction)
communities = {int(k): v for k, v in analysis['communities'].items()}
to_graphml(G, communities, 'graphify-out/graph.graphml')
print('graph.graphml written - open in Gephi, yEd, or any GraphML tool')
"
Step 7d - MCP server (only if --mcp flag)
python -m graphify.serve graphify-out/graph.json
This starts a stdio MCP server that exposes tools: query_graph, get_node, get_neighbors, get_community, god_nodes, graph_stats, shortest_path. Add to Claude Desktop or any MCP-compatible agent orchestrator so other agents can query the graph live.
To configure in Claude Desktop, add to claude_desktop_config.json:
{
"mcpServers": {
"graphify": {
"command": "python",
"args": ["-m", "graphify.serve", "/absolute/path/to/graphify-out/graph.json"]
}
}
}
Step 8 - Token reduction benchmark (only if total_words > 5000)
If total_words from .graphify_detect.json is greater than 5,000, run:
python -c "
import json
from graphify.benchmark import run_benchmark, print_benchmark
from pathlib import Path
detection = json.loads(Path('.graphify_detect.json').read_text())
result = run_benchmark('graphify-out/graph.json', corpus_words=detection['total_words'])
print_benchmark(result)
"
Print the output directly in chat. If total_words <= 5000, skip silently - the graph value is structural clarity, not token compression, for small corpora.
Step 9 - Save manifest, update cost tracker, clean up, and report
python -c "
import json
from pathlib import Path
from datetime import datetime, timezone
from graphify.detect import save_manifest
# Save manifest for --update
detect = json.loads(Path('.graphify_detect.json').read_text())
save_manifest(detect['files'])
# Update cumulative cost tracker
extract = json.loads(Path('.graphify_extract.json').read_text())
input_tok = extract.get('input_tokens', 0)
output_tok = extract.get('output_tokens', 0)
cost_path = Path('graphify-out/cost.json')
if cost_path.exists():
cost = json.loads(cost_path.read_text())
else:
cost = {'runs': [], 'total_input_tokens': 0, 'total_output_tokens': 0}
cost['runs'].append({
'date': datetime.now(timezone.utc).isoformat(),
'input_tokens': input_tok,
'output_tokens': output_tok,
'files': detect.get('total_files', 0),
})
cost['total_input_tokens'] += input_tok
cost['total_output_tokens'] += output_tok
cost_path.write_text(json.dumps(cost, indent=2))
print(f'This run: {input_tok:,} input tokens, {output_tok:,} output tokens')
print(f'All time: {cost[\"total_input_tokens\"]:,} input, {cost[\"total_output_tokens\"]:,} output ({len(cost[\"runs\"])} runs)')
"
Remove-Item -ErrorAction SilentlyContinue .graphify_detect.json, .graphify_extract.json, .graphify_ast.json, .graphify_semantic.json, .graphify_analysis.json, .graphify_labels.json
Remove-Item -ErrorAction SilentlyContinue graphify-out/.needs_update
Tell the user (omit the obsidian line unless --obsidian was given):
Graph complete. Outputs in PATH_TO_DIR/graphify-out/
graph.html - interactive graph, open in browser
GRAPH_REPORT.md - audit report
graph.json - raw graph data
obsidian/ - Obsidian vault (only if --obsidian was given)
If graphify saved you time, consider supporting it: https://github.com/sponsors/safishamsi
Replace PATH_TO_DIR with the actual absolute path of the directory that was processed.
Then paste these sections from GRAPH_REPORT.md directly into the chat:
- God Nodes
- Surprising Connections
- Suggested Questions
Do NOT paste the full report - just those three sections. Keep it concise.
Then immediately offer to explore. Pick the single most interesting suggested question from the report - the one that crosses the most community boundaries or has the most surprising bridge node - and ask:
"The most interesting question this graph can answer: [question]. Want me to trace it?"
If the user says yes, run /graphify query "[question]" on the graph and walk them through the answer using the graph structure - which nodes connect, which community boundaries get crossed, what the path reveals. Keep going as long as they want to explore. Each answer should end with a natural follow-up ("this connects to X - want to go deeper?") so the session feels like navigation, not a one-shot report.
The graph is the map. Your job after the pipeline is to be the guide.
For --update (incremental re-extraction)
Use when you've added or modified files since the last run. Only re-extracts changed files - saves tokens and time.
python -c "
import sys, json
from graphify.detect import detect_incremental, save_manifest
from pathlib import Path
result = detect_incremental(Path('INPUT_PATH'))
new_total = result.get('new_total', 0)
print(json.dumps(result, indent=2))
Path('.graphify_incremental.json').write_text(json.dumps(result))
if new_total == 0:
print('No files changed since last run. Nothing to update.')
raise SystemExit(0)
print(f'{new_total} new/changed file(s) to re-extract.')
"
If new files exist, first check whether all changed files are code files:
python -c "
import json
from pathlib import Path
result = json.loads(open('.graphify_incremental.json').read()) if Path('.graphify_incremental.json').exists() else {}
code_exts = {'.py','.ts','.js','.go','.rs','.java','.cpp','.c','.rb','.swift','.kt','.cs','.scala','.php','.cc','.cxx','.hpp','.h','.kts','.lua','.toc'}
new_files = result.get('new_files', {})
all_changed = [f for files in new_files.values() for f in files]
code_only = all(Path(f).suffix.lower() in code_exts for f in all_changed)
print('code_only:', code_only)
"
If code_only is True: print [graphify update] Code-only changes detected - skipping semantic extraction (no LLM needed), run only Step 3A (AST) on the changed files, skip Step 3B entirely (no subagents), then go straight to merge and Steps 4–8.
If code_only is False (any changed file is a doc/paper/image): run the full Steps 3A–3C pipeline as normal.
Then:
python -c "
import sys, json
from graphify.build import build_from_json
from graphify.export import to_json
from networkx.readwrite import json_graph
import networkx as nx
from pathlib import Path
# Load existing graph
existing_data = json.loads(Path('graphify-out/graph.json').read_text())
G_existing = json_graph.node_link_graph(existing_data, edges='links')
# Load new extraction
new_extraction = json.loads(Path('.graphify_extract.json').read_text())
G_new = build_from_json(new_extraction)
# Merge: new nodes/edges into existing graph
G_existing.update(G_new)
print(f'Merged: {G_existing.number_of_nodes()} nodes, {G_existing.number_of_edges()} edges')
"
Then run Steps 4–8 on the merged graph as normal.
After Step 4, show the graph diff:
python -c "
import json
from graphify.analyze import graph_diff
from graphify.build import build_from_json
from networkx.readwrite import json_graph
import networkx as nx
from pathlib import Path
# Load old graph (before update) from backup written before merge
old_data = json.loads(Path('.graphify_old.json').read_text()) if Path('.graphify_old.json').exists() else None
new_extract = json.loads(Path('.graphify_extract.json').read_text())
G_new = build_from_json(new_extract)
if old_data:
G_old = json_graph.node_link_graph(old_data, edges='links')
diff = graph_diff(G_old, G_new)
print(diff['summary'])
if diff['new_nodes']:
print('New nodes:', ', '.join(n['label'] for n in diff['new_nodes'][:5]))
if diff['new_edges']:
print('New edges:', len(diff['new_edges']))
"
Before the merge step, save the old graph: Copy-Item graphify-out/graph.json .graphify_old.json
Clean up after: Remove-Item -ErrorAction SilentlyContinue .graphify_old.json
For --cluster-only
Skip Steps 1–3. Load the existing graph from graphify-out/graph.json and re-run clustering:
python -c "
import sys, json
from graphify.cluster import cluster, score_all
from graphify.analyze import god_nodes, surprising_connections
from graphify.report import generate
from graphify.export import to_json
from networkx.readwrite import json_graph
import networkx as nx
from pathlib import Path
data = json.loads(Path('graphify-out/graph.json').read_text())
G = json_graph.node_link_graph(data, edges='links')
detection = {'total_files': 0, 'total_words': 99999, 'needs_graph': True, 'warning': None,
'files': {'code': [], 'document': [], 'paper': []}}
tokens = {'input': 0, 'output': 0}
communities = cluster(G)
cohesion = score_all(G, communities)
gods = god_nodes(G)
surprises = surprising_connections(G, communities)
labels = {cid: 'Community ' + str(cid) for cid in communities}
report = generate(G, communities, cohesion, labels, gods, surprises, detection, tokens, '.')
Path('graphify-out/GRAPH_REPORT.md').write_text(report)
to_json(G, communities, 'graphify-out/graph.json')
analysis = {
'communities': {str(k): v for k, v in communities.items()},
'cohesion': {str(k): v for k, v in cohesion.items()},
'gods': gods,
'surprises': surprises,
}
Path('.graphify_analysis.json').write_text(json.dumps(analysis, indent=2))
print(f'Re-clustered: {len(communities)} communities')
"
Then run Steps 5–9 as normal (label communities, generate viz, benchmark, clean up, report).
For /graphify query
Two traversal modes - choose based on the question:
| Mode | Flag | Best for |
|---|---|---|
| BFS (default) | (none) | "What is X connected to?" - broad context, nearest neighbors first |
| DFS | --dfs | "How does X reach Y?" - trace a specific chain or dependency path |
First check the graph exists:
python -c "
from pathlib import Path
if not Path('graphify-out/graph.json').exists():
print('ERROR: No graph found. Run /graphify <path> first to build the graph.')
raise SystemExit(1)
"
If it fails, stop and tell the user to run /graphify <path> first.
Load graphify-out/graph.json, then:
- Find the 1-3 nodes whose label best matches key terms in the question.
- Run the appropriate traversal from each starting node.
- Read the subgraph - node labels, edge relations, confidence tags, source locations.
- Answer using only what the graph contains. Quote
source_locationwhen citing a specific fact. - If the graph lacks enough information, say so - do not hallucinate edges.
python -c "
import sys, json
from networkx.readwrite import json_graph
import networkx as nx
from pathlib import Path
data = json.loads(Path('graphify-out/graph.json').read_text())
G = json_graph.node_link_graph(data, edges='links')
question = 'QUESTION'
mode = 'MODE' # 'bfs' or 'dfs'
terms = [t.lower() for t in question.split() if len(t) > 3]
# Find best-matching start nodes
scored = []
for nid, ndata in G.nodes(data=True):
label = ndata.get('label', '').lower()
score = sum(1 for t in terms if t in label)
if score > 0:
scored.append((score, nid))
scored.sort(reverse=True)
start_nodes = [nid for _, nid in scored[:3]]
if not start_nodes:
print('No matching nodes found for query terms:', terms)
sys.exit(0)
subgraph_nodes = set()
subgraph_edges = []
if mode == 'dfs':
# DFS: follow one path as deep as possible before backtracking.
# Depth-limited to 6 to avoid traversing the whole graph.
visited = set()
stack = [(n, 0) for n in reversed(start_nodes)]
while stack:
node, depth = stack.pop()
if node in visited or depth > 6:
continue
visited.add(node)
subgraph_nodes.add(node)
for neighbor in G.neighbors(node):
if neighbor not in visited:
stack.append((neighbor, depth + 1))
subgraph_edges.append((node, neighbor))
else:
# BFS: explore all neighbors layer by layer up to depth 3.
frontier = set(start_nodes)
subgraph_nodes = set(start_nodes)
for _ in range(3):
next_frontier = set()
for n in frontier:
for neighbor in G.neighbors(n):
if neighbor not in subgraph_nodes:
next_frontier.add(neighbor)
subgraph_edges.append((n, neighbor))
subgraph_nodes.update(next_frontier)
frontier = next_frontier
# Token-budget aware output: rank by relevance, cut at budget (~4 chars/token)
token_budget = BUDGET # default 2000
char_budget = token_budget * 4
# Score each node by term overlap for ranked output
def relevance(nid):
label = G.nodes[nid].get('label', '').lower()
return sum(1 for t in terms if t in label)
ranked_nodes = sorted(subgraph_nodes, key=relevance, reverse=True)
lines = [f'Traversal: {mode.upper()} | Start: {[G.nodes[n].get(\"label\",n) for n in start_nodes]} | {len(subgraph_nodes)} nodes']
for nid in ranked_nodes:
d = G.nodes[nid]
lines.append(f' NODE {d.get(\"label\", nid)} [src={d.get(\"source_file\",\"\")} loc={d.get(\"source_location\",\"\")}]')
for u, v in subgraph_edges:
if u in subgraph_nodes and v in subgraph_nodes:
d = G.edges[u, v]
lines.append(f' EDGE {G.nodes[u].get(\"label\",u)} --{d.get(\"relation\",\"\")} [{d.get(\"confidence\",\"\")}]--> {G.nodes[v].get(\"label\",v)}')
output = '\n'.join(lines)
if len(output) > char_budget:
output = output[:char_budget] + f'\n... (truncated at ~{token_budget} token budget - use --budget N for more)'
print(output)
"
Replace QUESTION with the user's actual question, MODE with bfs or dfs, and BUDGET with the token budget (default 2000, or whatever --budget N specifies). Then answer based on the subgraph output above.
After writing the answer, save it back into the graph so it improves future queries:
python -m graphify save-result --question "QUESTION" --answer "ANSWER" --type query --nodes NODE1 NODE2
Replace QUESTION with the question, ANSWER with your full answer text, SOURCE_NODES with the list of node labels you cited. This closes the feedback loop: the next --update will extract this Q&A as a node in the graph.
For /graphify path
Find the shortest path between two named concepts in the graph.
First check the graph exists:
python -c "
from pathlib import Path
if not Path('graphify-out/graph.json').exists():
print('ERROR: No graph found. Run /graphify <path> first to build the graph.')
raise SystemExit(1)
"
If it fails, stop and tell the user to run /graphify <path> first.
python -c "
import json, sys
import networkx as nx
from networkx.readwrite import json_graph
from pathlib import Path
data = json.loads(Path('graphify-out/graph.json').read_text())
G = json_graph.node_link_graph(data, edges='links')
a_term = 'NODE_A'
b_term = 'NODE_B'
def find_node(term):
term = term.lower()
scored = sorted(
[(sum(1 for w in term.split() if w in G.nodes[n].get('label','').lower()), n)
for n in G.nodes()],
reverse=True
)
return scored[0][1] if scored and scored[0][0] > 0 else None
src = find_node(a_term)
tgt = find_node(b_term)
if not src or not tgt:
print(f'Could not find nodes matching: {a_term!r} or {b_term!r}')
sys.exit(0)
try:
path = nx.shortest_path(G, src, tgt)
print(f'Shortest path ({len(path)-1} hops):')
for i, nid in enumerate(path):
label = G.nodes[nid].get('label', nid)
if i < len(path) - 1:
edge = G.edges[nid, path[i+1]]
rel = edge.get('relation', '')
conf = edge.get('confidence', '')
print(f' {label} --{rel}--> [{conf}]')
else:
print(f' {label}')
except nx.NetworkXNoPath:
print(f'No path found between {a_term!r} and {b_term!r}')
except nx.NodeNotFound as e:
print(f'Node not found: {e}')
"
Replace NODE_A and NODE_B with the actual concept names from the user. Then explain the path in plain language - what each hop means, why it's significant.
After writing the explanation, save it back:
python -m graphify save-result --question "Path from NODE_A to NODE_B" --answer "ANSWER" --type path_query --nodes NODE_A NODE_B
For /graphify explain
Give a plain-language explanation of a single node - everything connected to it.
First check the graph exists:
python -c "
from pathlib import Path
if not Path('graphify-out/graph.json').exists():
print('ERROR: No graph found. Run /graphify <path> first to build the graph.')
raise SystemExit(1)
"
If it fails, stop and tell the user to run /graphify <path> first.
python -c "
import json, sys
import networkx as nx
from networkx.readwrite import json_graph
from pathlib import Path
data = json.loads(Path('graphify-out/graph.json').read_text())
G = json_graph.node_link_graph(data, edges='links')
term = 'NODE_NAME'
term_lower = term.lower()
# Find best matching node
scored = sorted(
[(sum(1 for w in term_lower.split() if w in G.nodes[n].get('label','').lower()), n)
for n in G.nodes()],
reverse=True
)
if not scored or scored[0][0] == 0:
print(f'No node matching {term!r}')
sys.exit(0)
nid = scored[0][1]
data_n = G.nodes[nid]
print(f'NODE: {data_n.get(\"label\", nid)}')
print(f' source: {data_n.get(\"source_file\",\"unknown\")}')
print(f' type: {data_n.get(\"file_type\",\"unknown\")}')
print(f' degree: {G.degree(nid)}')
print()
print('CONNECTIONS:')
for neighbor in G.neighbors(nid):
edge = G.edges[nid, neighbor]
nlabel = G.nodes[neighbor].get('label', neighbor)
rel = edge.get('relation', '')
conf = edge.get('confidence', '')
src_file = G.nodes[neighbor].get('source_file', '')
print(f' --{rel}--> {nlabel} [{conf}] ({src_file})')
"
Replace NODE_NAME with the concept the user asked about. Then write a 3-5 sentence explanation of what this node is, what it connects to, and why those connections are significant. Use the source locations as citations.
After writing the explanation, save it back:
python -m graphify save-result --question "Explain NODE_NAME" --answer "ANSWER" --type explain --nodes NODE_NAME
For /graphify add
Fetch a URL and add it to the corpus, then update the graph.
python -c "
import sys
from graphify.ingest import ingest
from pathlib import Path
try:
out = ingest('URL', Path('./raw'), author='AUTHOR', contributor='CONTRIBUTOR')
print(f'Saved to {out}')
except ValueError as e:
print(f'error: {e}', file=sys.stderr)
sys.exit(1)
except RuntimeError as e:
print(f'error: {e}', file=sys.stderr)
sys.exit(1)
"
Replace URL with the actual URL, AUTHOR with the user's name if provided, CONTRIBUTOR likewise. If the command exits with an error, tell the user what went wrong - do not silently continue. After a successful save, automatically run the --update pipeline on ./raw to merge the new file into the existing graph.
Supported URL types (auto-detected):
- Twitter/X → fetched via oEmbed, saved as
.mdwith tweet text and author - arXiv → abstract + metadata saved as
.md - PDF → downloaded as
.pdf - Images (.png/.jpg/.webp) → downloaded, vision extraction runs on next build
- Any webpage → converted to markdown via html2text
For --watch
Start a background watcher that monitors a folder and auto-updates the graph when files change.
python -m graphify.watch INPUT_PATH --debounce 3
Replace INPUT_PATH with the folder to watch. Behavior depends on what changed:
- Code files only (.py, .ts, .go, etc.): re-runs AST extraction + rebuild + cluster immediately, no LLM needed.
graph.jsonandGRAPH_REPORT.mdare updated automatically. - Docs, papers, or images: writes a
graphify-out/needs_updateflag and prints a notification to run/graphify --update(LLM semantic re-extraction required).
Debounce (default 3s): waits until file activity stops before triggering, so a wave of parallel agent writes doesn't trigger a rebuild per file.
Press Ctrl+C to stop.
For agentic workflows: run --watch in a background terminal. Code changes from agent waves are picked up automatically between waves. If agents are also writing docs or notes, you'll need a manual /graphify --update after those waves.
For git commit hook
Install a post-commit hook that auto-rebuilds the graph after every commit. No background process needed - triggers once per commit, works with any editor.
graphify hook install # install
graphify hook uninstall # remove
graphify hook status # check
After every git commit, the hook detects which code files changed (via git diff HEAD~1), re-runs AST extraction on those files, and rebuilds graph.json and GRAPH_REPORT.md. Doc/image changes are ignored by the hook - run /graphify --update manually for those.
If a post-commit hook already exists, graphify appends to it rather than replacing it.
For native CLAUDE.md integration
Run once per project to make graphify always-on in Claude Code sessions:
graphify claude install
This writes a ## graphify section to the local CLAUDE.md that instructs Claude to check the graph before answering codebase questions and rebuild it after code changes. No manual /graphify needed in future sessions.
graphify claude uninstall # remove the section
Troubleshooting
PowerShell 5.1: Vertical scrolling stops working
If vertical scrolling breaks in PowerShell after running graphify, this is caused by ANSI escape sequences from the graspologic library. Graphify v0.3.10+ suppresses this output, but if you still see the issue:
- Upgrade graphify:
pip install --upgrade graphifyy - Use Windows Terminal instead of the legacy PowerShell console — Windows Terminal handles ANSI codes correctly
- Reset your terminal: close and reopen PowerShell
- Skip graspologic: uninstall it (
pip uninstall graspologic) and graphify will fall back to NetworkX's built-in Louvain algorithm, which produces no ANSI output
Honesty Rules
- Never invent an edge. If unsure, use AMBIGUOUS.
- Never skip the corpus check warning.
- Always show token cost in the report.
- Never hide cohesion scores behind symbols - show the raw number.
- Never run HTML viz on a graph with more than 5,000 nodes without warning the user.
Verification
- Install check passed (or the user approved installation) before any pipeline step ran
- The corpus summary was shown, and the large-corpus warning was honored when triggered
- Semantic extraction used parallel subagents dispatched in a single message — not sequential self-reads
- The empty-graph error stopped the run instead of proceeding to labeling or visualization
- The expected outputs exist under the graphify-out directory, and the run's token cost was reported
- Only the three report sections were pasted into chat, followed by the exploration offer
- Every edge carries an EXTRACTED, INFERRED, or AMBIGUOUS tag — nothing invented
MarkItDown File Intake
Purpose
Convert supported files or URLs into Markdown before inspection. This reduces token cost and makes binary or structured inputs easier to analyze.
When to Use
- User provides a local file in a format Microsoft MarkItDown supports.
- User provides a supported URL and Markdown conversion will improve inspection.
- Source is binary or structurally noisy enough that direct inspection is inefficient.
Do not use when:
- File is already clean text.
- User explicitly wants raw binary or metadata-only handling.
- Another tool is clearly better for the task.
Requirements
Required tool:
- Microsoft MarkItDown
Check:
Get-Command markitdown -ErrorAction SilentlyContinue
python -m markitdown --help
Install:
python -m pip install markitdown
Rules:
- Do not assume MarkItDown is installed.
- Do not install it without user approval.
- Show the install command before running it.
- Prefer user-local or project-local installation when practical.
Inputs
- File path or URL to convert.
- Optional output path for the generated Markdown.
Workflow
- Check whether MarkItDown is available.
- If missing, tell the user before attempting conversion.
- Convert with Microsoft MarkItDown or the helper script in
references/.
markitdown <path-or-url> -o output.md
powershell -ExecutionPolicy Bypass -File "references\convert_with_markitdown.ps1" -Source "<path-or-url>"
- Confirm output path exists and file is non-empty.
- Inspect the generated Markdown with narrow reads first.
- Tell the user MarkItDown was used.
Output
- Path to the generated Markdown file
- Inspection results based on that Markdown
Verification
- MarkItDown availability was checked first
- No conversion was claimed if the tool was missing
- Generated Markdown file exists and is non-empty
- Inspection used the generated Markdown, not the original binary
Failure Modes
- Unsupported or weak conversion output
- Audio formats needing extra tooling such as
ffmpeg - Remote URL access failure
- Empty or garbled Markdown output
Missing Dependency Behavior
If MarkItDown is missing:
- Say conversion did not happen.
- Tell the user Microsoft MarkItDown is required.
- Ask before installing it.
- Show the install command.
- Fall back to manual inspection when practical.
Memory Build Workflow
Overview
Build persistent graph memory with graphify.
Use helper tools only when source format would otherwise reduce graph quality or waste context.
When to Use
- first graph build for a repo, notes folder, research corpus, or mixed raw folder
- corpus changed enough that persistent graph memory is worth refreshing
- input includes PDFs, Office docs, or noisy web pages that should be normalized before graph build
- user wants durable graph outputs instead of one-shot file reading
Do not use for:
- one small plain-text file or a narrow one-off question
- cases where an existing graph already answers the question better via query
Required Checks
apx check graphify
apx check markitdown-file-intake
apx check defuddle
Stop and report missing tools. Do not auto-install without approval.
Routing
| Situation | Action |
|---|---|
| ready local corpus of readable files | run graphify |
| existing graph plus changed sources | run graphify --update |
| PDF, Office doc, slide deck, or similar hard-to-read format | convert with markitdown-file-intake, then build with graphify |
| article or noisy web page | clean with defuddle, then build with graphify |
| user wants vault browsing after build | offer optional Obsidian export |
Core Rules
graphifyis the primary engine- prefer
graphify --updateover full rebuild when a graph already exists - use helpers only to improve source readability before graph ingestion
- keep Obsidian optional and post-build
- keep source provenance intact when converting inputs
Minimal Workflow
- Check whether a usable graph already exists.
- If it exists and sources changed, prefer
graphify --update. - If sources are noisy or binary, normalize them with the narrowest helper.
- Build or refresh with
graphify. - Offer query workflow next instead of rereading the corpus.
Common Failure Modes
- missing
graphify: stop and report; no fallback build path - rebuilding from scratch when update would work: unnecessary cost and churn
- using helpers on already-readable Markdown or code: wasted step
- treating Obsidian as required: wrong; it is optional output only
Verification
- Required tool checks ran; missing tools were reported, not auto-installed
- An existing usable graph was checked for before any build
- Incremental update was preferred over full rebuild when a graph existed
- Helpers were used only on sources that would otherwise degrade graph quality
- Source provenance survived any conversion; Obsidian was offered, never assumed
References
Memory Optimization Workflow
Overview
Minimize token spend, reread cost, and unnecessary rebuilds.
graphify is the main optimization path for repeated work. Helper tools exist to make hard sources cheaper before graph or direct reading.
When to Use
- mixed corpus and the cheapest inspection path is unclear
- repeated questions over the same files
- need to choose between direct read, conversion, graph build, update, or query
- want to reduce repeated large-context rereads
Do not use for:
- tiny single-file questions where direct reading is already cheapest
- cases where the user explicitly wants raw-file inspection only
Required Checks
apx check graphify
apx check markitdown-file-intake
apx check defuddle
Stop and report missing tools. Do not auto-install without approval.
Fast Routing
| Situation | Cheapest path |
|---|---|
| small readable text corpus, one question | read directly |
| PDF, Office doc, or other binary-like source | markitdown-file-intake |
| noisy web page or article | defuddle |
| repeated questions across same corpus | build with graphify |
| existing graph plus changed sources | graphify --update |
| existing graph plus new question | query graph first |
Decision Rules
- prefer direct reading for small plain-text scope
- prefer Markdown over binary or chrome-heavy formats
- prefer graph query over full reread when a graph already exists
- prefer incremental update over rebuild
- keep helper tools secondary to the main graph path
- keep Obsidian optional; it is not part of the optimization decision unless the user wants vault browsing
Escalation Ladder
- Direct read if scope is already small and readable.
- Convert only if format is the main source of waste.
- Build graph memory when questions will repeat or corpus is broad.
- Update existing graph when sources changed.
- Query existing graph before any broad reread.
Common Failure Modes
- building a graph for a tiny one-shot question
- rereading large corpora after a graph already exists
- converting already-readable Markdown or code
- rebuilding instead of updating
- making helper tools feel primary instead of supportive
Verification
- Required tool checks ran; missing tools were reported, not auto-installed
- The chosen path matches the routing table — direct read for small readable scope
- No graph was built for a tiny one-shot question
- An existing graph was queried or updated instead of rereading the corpus
- Helpers stayed secondary to the main graph path
References
Memory Query Workflow
Overview
Use existing graph memory first.
Query the graph before rereading source files unless the graph is missing, stale, or too weak for the question.
Required Check
apx check graphify
Required State
- existing
graphify-out/graph.json
Routing
| Question shape | Action |
|---|---|
| broad question about connected concepts | graphify query |
| trace between two concepts, files, or systems | graphify path |
| explain one concept or node in context | graphify explain |
| no graph exists | switch to memory-build-workflow |
| graph exists but corpus changed | recommend graphify --update before trusting results |
Core Rules
- prefer graph retrieval over full-corpus reread
- say explicitly when the graph is missing, stale, sparse, or weakly matched
- do not overclaim beyond what graph nodes and edges support
- when graph coverage is weak, use the graph result to target the next direct read instead of restarting broad exploration
Minimal Workflow
- Confirm
graphify-out/graph.jsonexists. - Choose
query,path, orexplainbased on question shape. - Answer from graph evidence first.
- If result quality is weak, say why: missing graph, stale graph, low coverage, or weak node match.
- Escalate to build/update or targeted reread only when needed.
Common Failure Modes
- skipping graph lookup and rereading everything
- hiding that the graph is stale or incomplete
- using
queryfor a question that clearly needs a path trace - treating no-result output as proof the corpus lacks the concept
Verification
- Graph existence was confirmed before any query ran
- The command matched the question shape: query for breadth, path for traces, explain for one node
- The answer is grounded in graph nodes and edges — no overclaiming
- Staleness, sparseness, or weak node matches were stated explicitly
- Escalation to build, update, or targeted reread happened only when graph evidence was insufficient
Reference
Search Before Building
Before implementing new functionality, verify it does not already exist and that the best option has been considered.
When to Use
- About to add a new helper, utility, or abstraction
- Task says "add X" and X sounds like a solved problem
- Considering a new external dependency
- Agent proposes writing something from scratch without checking first
Four-Step Check
Run in order. Stop when you find a satisfactory answer.
Step 1 — Repo-first
Search the current codebase before anything else:
rg "<keyword>" src/ lib/ --type ts --type js -l
rg "<keyword>" --glob "*.py" -l
Check: Does equivalent logic already exist? Is it importable as-is, or would it need wrapper work?
Step 2 — Package registry
Search the relevant registry for the project language:
| Language | Registry | Search method |
|---|---|---|
| TypeScript/JS | npm | npm search <keyword> or npmjs.com |
| Python | PyPI | pip index search <keyword> or pypi.org |
| Go | pkg.go.dev | web search site:pkg.go.dev <keyword> |
| Rust | crates.io | cargo search <keyword> |
Score each candidate:
- Maintenance: last commit < 1 year, open issues ratio
- Popularity: weekly downloads or GitHub stars
- License: MIT / Apache-2.0 / BSD preferred; check for GPL/commercial constraints
- Size: avoid heavy packages for a single feature
Step 3 — MCP / tool servers
Check whether an MCP server already provides this capability:
# List currently configured MCP servers
cat .mcp.json 2>/dev/null || cat ~/.claude/settings.json | grep -A5 '"mcpServers"'
Check the Agent Powerups catalog for MCP configs:
apx list --type mcp-config
If a server covers the need, prefer configuring it over writing code.
Step 4 — Maintenance and license risk
Before adopting a package, verify:
- Not abandoned (last release within 18 months)
- License compatible with this project
- No known critical CVEs (
npm audit/pip-audit/cargo audit) - Dependency count is reasonable (< 20 transitive for small utilities)
Decision
| Finding | Action |
|---|---|
| Exact match in repo | Reuse — import and use; refactor only if the interface is incompatible |
| Exact external match, acceptable risk | Adopt — install and use directly; do not wrap unless the API is hostile |
| Partial match | Wrap — install, write a thin adapter; keep the adapter < 50 lines |
| Multiple weak matches | Compose — combine 2–3 small packages; document why |
| No suitable option | Build — write custom code; document the gap search found |
Constraint: Do Not Skip
This check is mandatory before:
- Writing any utility over 20 lines that solves a generic problem
- Adding a new external dependency
- Configuring a new MCP server
If time-boxed, spend at most 5 minutes on Steps 1–2 before deciding.
Anti-Patterns
- Repo-skip: Writing code without checking if an internal equivalent exists
- Registry-skip: Adding a package without checking simpler alternatives
- Over-wrapping: Encapsulating a library so heavily that the benefits are lost
- Dependency bloat: Pulling in a 5 MB package for a single 10-line feature
Verification
- The Step 1 repo search ran before any custom code was written
- Registry candidates were scored on maintenance, popularity, license, and size
- MCP/tool-server coverage was checked before writing new integration code
- Any adopted package passed the abandonment, license, CVE, and dependency-count checks
- The decision (reuse / adopt / wrap / compose / build) is recorded — and for build, the gap the search found is documented
Using Powerups
Purpose
Find and apply installed Agent Powerups before improvising. A powerup is useful only after you discover likely matches, inspect the actual asset, follow its instructions, and verify the user task with task-specific evidence.
When to Use
Use at the start of non-trivial work, and again when the task changes shape.
Use when the user asks for debugging, planning, review, setup, file intake, cleanup, PR triage, second opinions, MCP config, hooks, commands, or AGENTS.md templates.
Do not force a powerup when none fits. Say no matching powerup applies and proceed normally.
Inputs
- User task.
- Current repo or agent root.
- Installed
agent-powerupslocation, usuallyagent-powerups/under the agent root or the package repo. - Optional CLI access to
apxfor discovery and inventory. - Optional installed discovery index file; treat it as a derived snapshot, not the source of truth.
Workflow
- Discover or match available assets.
Use target-specific routing:
- Claude Code: start with native skill discovery when skills are already exposed by the host. Use
apx discoverwhen the task is uncertain, when no native skill clearly fits, or when the task may need non-skill assets. - Codex, Gemini, and generic agents: start with
apx discover. - All targets: use
apx inventoryfor MCP configs, hooks, AGENTS.md templates, plugin-contained assets, staged assets, and installed-only assets.
apx discover "<user task>" --target <codex|claude-code|gemini|generic>
apx inventory --target <codex|claude-code|gemini|generic> --json
apx list --json --verbose
apx plugins list
If apx is unavailable, inspect local folders: skills/, commands/, mcp/, agents-md/, hooks/, workflows/.
- Match the task to assets.
Prefer the narrowest high-ranked asset whose description matches the current task. Treat apx discover output as a shortlist, not as proof that a powerup has been used.
Examples:
| Task signal | Asset type to inspect |
|---|---|
| bug, failing test, regression | debugging skill |
| implementation spec | planning skill |
| file or URL intake | file-intake skill |
| pre-handoff validation | command |
| local MCP setup | MCP config |
| repo instruction baseline | AGENTS.md template |
- Read before using.
For a candidate asset:
apx info <name>
Then read the asset file. Do not rely only on the catalog summary.
Most powerups do not require step 4. Only use apx check when the asset declares external requirements or its own instructions say a dependency check is needed. Do not run apx check for every asset by default.
- Check requirements.
If apx check reports a missing command or package, stop and say exactly what is missing. Use apx check <asset> --install-missing --dry-run to preview supported installers. Ask before running --install-missing --yes. Do not pretend conversion, fetch, review, or CLI delegation happened when the tool was unavailable.
- Apply conservatively.
Follow the asset instructions. Keep scope local to the user task. For GitHub MCP, use apx mcp check github-local, apx mcp smoke github-local, then apx mcp install github-local --target <agent> --dry-run before any --yes install. For hooks, treat recipes as review-before-use; do not enable them automatically.
- Report use.
Final response should name:
- powerup used
- requirement check result, or
not needed - important fallback or skipped asset
- task-specific validation performed
Output
When a powerup applies:
Used: <asset-name>
Why: <task signal>
Requirements: <OK / missing / not needed>
Result: <how it changed the work>
Validation: <real task-specific checks, not apx check>
When none applies:
No matching Agent Powerup found. Proceeded with normal repo inspection.
Verification
Before claiming setup or use succeeded:
- Asset was read, not guessed from name.
- Requirements were checked only when the selected asset declared external dependencies.
- Missing tools were reported, not bypassed silently.
apx checkoutput was not presented as proof that the skill was used or the task succeeded.- No secrets were written.
- No global config, shell profile, hook, MCP server, or dependency install was changed without explicit user approval.
Failure Modes
- Catalog missing: inspect local asset folders directly, then report that
apxcatalog discovery failed. - Missing dependency: stop that asset path; ask before install; use a lower-capability fallback if safe.
- No matching asset: say so and continue normally.
- Unsafe asset request: print manual review steps instead of mutating config.
- Multiple possible assets: choose the narrowest one; mention skipped alternatives only when relevant.
Commands 3
Objective
Build persistent graph-backed memory for a corpus. graphify is primary engine. defuddle and markitdown are preprocessing helpers only.
Context
Inputs:
- target path from
$ARGUMENTS, default.when omitted --updateto refresh an existing graph instead of rebuilding from scratch--obsidianonly when the user explicitly wants vault-style navigation
Expected outputs:
graphify-out/graph.json- updated graph report or other
graphify-out/artifacts from the graphify workflow - optional
graphify-out/obsidian/only when--obsidianwas requested
Process
- Resolve target path. Default to current directory. Confirm it exists before any tool invocation.
- Check requirements:
apx check graphifyapx check markitdown-file-intakeapx check defuddle
- If
graphifyis missing, stop immediately. Report the missing requirement and point toapx check graphify --install-missing --dry-run. Do not continue with helper-only output. - Inspect the corpus and choose one primary route:
- ready docs/code/notes/images -> run
graphifydirectly - web-heavy HTML/docs -> use
defuddlefirst only if HTML chrome would pollute the graph - PDF/Office docs -> use
markitdown-file-intakefirst only if direct input would be noisy or unreadable - mixed corpus -> normalize only the noisy subsets, then hand the corpus to
graphify
- ready docs/code/notes/images -> run
- Decide build mode:
- if
graphify-out/graph.jsonalready exists, prefer update flow - if user passed
--update, use update flow even if only part of the corpus changed - if no graph exists yet, run a fresh build
- if
- Keep Obsidian optional:
- if
--obsidianwas requested, include Obsidian export in the graphify run - otherwise do not add vault generation by default
- if
- Report what happened:
- chosen route
- requirement status
- whether this was fresh build or update
- exact next step if the build was blocked
Stop Conditions
- target path does not exist or is clearly the wrong scope
graphifyrequirement check fails- no supported or readable source material is found after inspection
- helper conversion is needed for source quality, but the required helper is missing
- user asked for
--updatebut there is no existing graph to update; switch to fresh build only if the user intent still clearly fits
Rules
graphifyis always the primary product and final engine- helpers are normalization tools, not substitutes for graph build
- never pretend a build, refresh, or export succeeded when requirements are missing
- prefer update over rebuild when an existing graph can be preserved
- do not require Obsidian for successful completion
- when a helper is missing, fall back to direct
graphifyonly if source quality is still acceptable; otherwise stop and say why - cite
skills/graphify/UPSTREAM.md,references/HELPER_TOOLS.md, andreferences/OBSIDIAN_EXPORT.md
Objective
Recommend the cheapest memory workflow that preserves answer quality and future reuse.
Context
Inputs:
- optional path or URL
- optional question or task goal
Optimization targets:
- lower token cost now
- lower reread cost later
- better persistence when repeated queries are likely
Process
- Inspect input shape and reuse horizon:
- plain text or small local file
- noisy web page
- PDF/Office doc or other hard-to-read binary-ish source
- mixed corpus
- existing graph with new question
- existing graph with changed sources
- Check requirements:
apx check graphifyapx check markitdown-file-intakeapx check defuddle
- Recommend exactly one primary path:
- direct read for small, simple, one-shot text
defuddle-> Markdown -> read or build when web chrome is the main problemmarkitdown-file-intake-> Markdown -> read or build when document format is the main problemgraphifyfull build when repeated questions or relationship navigation justify persistent memorygraphify --updatewhen a graph already exists and sources changed- graph query against existing graph when the graph exists and the task is retrieval, tracing, or explanation
- State why that path is cheapest:
- lower immediate token cost
- lower repeated reread cost
- better persistence across future sessions
- Include exact next command(s) for the recommended path.
- If a required tool for the best path is missing, either:
- recommend the next-best lower-capability path that still preserves answer quality, or
- stop and say the missing requirement makes the cheap path unavailable
Stop Conditions
- input is too ambiguous to choose between direct read, helper conversion, build, update, or query
- the recommended path depends on a missing tool and no credible fallback preserves answer quality
- user asks for persistent graph advice but the target path or URL is unavailable
Rules
- optimization target = lower token cost, lower reread cost, better persistence
graphifyis long-lived memory path- helpers are normalization tools only
- keep
graphifyprimary for persistent memory, helpers secondary, Obsidian optional - do not recommend a graph build for trivial one-shot text when direct read is cheaper
- do not claim a helper or graph path is available before requirement checks pass
- do not claim bundled upstream code
Objective
Use graph-backed memory first. Query existing graph state before reopening source documents.
Context
Input: a user question, node name, or relationship target from $ARGUMENTS.
Expected state:
graphify-out/graph.jsonalready exists for the target corpusgraphifyis available for query, path, or explain flows
Process
- Check
apx check graphify. - Confirm
graphify-out/graph.jsonexists before answering from graph memory. - If
graphifyis missing, stop and report the missing requirement. If the graph file is missing, stop and route tomemory-build. - Route the request to one primary flow:
- broad question, topic lookup, or "what do we know about X?" ->
graphify query - relationship trace, dependency chain, or "how does X connect to Y?" ->
graphify path - concept/node explanation or "explain X" ->
graphify explain
- broad question, topic lookup, or "what do we know about X?" ->
- Check freshness before leaning on the answer:
- if the corpus changed after the graph was built, say the graph may be stale
- recommend
memory-buildorgraphify --updatebefore treating the answer as current
- If the graph answer is weak, partial, or clearly off-route, say so explicitly and recommend either refresh or targeted source reread.
Stop Conditions
graphifyrequirement check failsgraphify-out/graph.jsondoes not exist- user is asking for current corpus state but the graph is known stale enough that the answer would mislead
- query intent is ambiguous enough that query/path/explain routing would likely choose the wrong flow
Rules
- prefer graph retrieval over corpus reread
- do not hallucinate edges, nodes, or freshness
- do not silently fall back to full-corpus reread unless the user asked for it or graph retrieval is unusable
- if graph answer is weak, say so and recommend refresh or targeted source read
graphify queryis default only for broad retrieval; usepathandexplainwhen the question shape is narrower
Agents 2
You are an APX graph memory curator.
Your job is to keep the workflow graph-first, operational, and honest. Route the user toward build, update, query, path, or explain actions without overselling freshness or completeness.
Operating stance:
- graph-backed memory first
- helper preprocessing second
- direct reading only when graph work is unnecessary
- Obsidian is optional output, never a prerequisite
- this bundle guides upstream tools; it does not ship or vendor them
Decide among these actions:
- build: no graph exists and reuse is likely
- update: graph exists but sources changed
- query: graph exists and user has a broad question
- path: graph exists and user wants how two concepts connect
- explain: graph exists and user wants one concept summarized from graph context
- hold: prerequisites missing or corpus is too small to justify graph work
Helper-tool rules:
- use
markitdown-file-intakefor PDFs, Office docs, and similar formats when raw input would be noisy or unreadable - use
defuddlefor article/webpage cleanup when page chrome would pollute the graph - skip helpers when source material is already clean Markdown, text, or code
Required caution:
- never assume
graphify,markitdown, ordefuddleare installed - recommend
apx check ...before execution - stop on missing requirements; do not fake the workflow
- do not claim a graph is current unless file state or user context supports it
- prefer
--updateover rebuild when the graph is still structurally usable
When you answer, be operational:
- Action:
build,update,query,path,explain, orhold - Why: one short explanation tied to corpus shape and user goal
- Checks: exact prerequisite checks and file-state checks
- Steps: minimal next commands or workflow handoff
- Fallback: what to do if the preferred graph path is blocked
You are an APX memory optimizer.
Your job is routing, not raw extraction. Look at the corpus shape, current graph state, and user goal, then choose the lowest-cost path that still answers the question well.
Default stance:
- prefer the smallest step that works
- treat
graphifyas the primary persistent memory engine - use helper tools only when they clearly improve input quality
- do not assume anything is installed
- do not claim bundled or vendored upstream code
What to inspect first:
- corpus size and file mix: plain text, code, PDFs, Office docs, web pages, images
- whether a graph already exists, usually
graphify-out/graph.json - whether the user needs a one-off answer, repeated reuse, or ongoing updates
- whether source formats are already readable enough without conversion
Routing rules:
- small, readable text/code corpus and one-off question -> direct read
- binary or awkward document formats -> Markdown conversion first
- noisy web content with lots of HTML chrome ->
defuddlefirst - repeated questions across the same corpus -> build graph memory with
graphify - existing graph + changed sources -> prefer
graphify --update - existing graph + new question -> query the graph before reopening source files
- optional vault/navigation needs -> mention Obsidian only after the graph path is already justified
Guardrails:
- recommend
apx check <tool>before any runnable step - stop and report missing tools instead of hand-waving past them
- do not invent graph freshness, coverage, or quality
- prefer update/query over rebuild when a usable graph already exists
- keep provenance clear: this bundle ships guidance, not upstream executables
Return format:
- Recommended path: one concrete route
- Why this is cheapest: short cost/benefit explanation
- Checks first: exact
apx check ...calls or file existence checks - Fallback if missing: what to do if the recommended tool is unavailable
- Notes: only if there is a real caveat about freshness, coverage, or optional Obsidian export
Sponsors
Details
- Marketplace
- yeaight7/agent-powerups
- Source
- plugins/memory-optimization
- Category
- Developer Tools
- License
- Apache-2.0
- Keywords
- graphify, memory, optimization, markdown, obsidian
More from yeaight7/agent-powerups
All 21- quality-gatesv0.6.3
- security-guardrailsv0.6.3
- skill-authoringv0.6.3
- software-engineeringv0.6.3
- spec-driven-developmentv0.6.3
- spec-quality-gatesv0.6.3
- tool-integrationsv0.6.3
- agent-evaluation-labv0.6.3
- agentic-systemsv0.6.3
- codebase-intelligencev0.6.3
- codebase-maintenancev0.6.3
- connected-appsv0.6.3
- context-efficiencyv0.6.3
- data-engineeringv0.6.3
- debugging-diagnosticsv0.6.3
- dev-vitalsv0.6.3
- documentation-systemsv0.6.3
- github-opsv0.6.3
- machine-learning-opsv0.6.3
- mcp-developmentv0.6.3