Claude Marketplaces
SkillsMCP serversMarketplacesDigestTools
Submit

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP servers by category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control
Claude Marketplaces

An independent directory of skills, plugins and MCP servers for Claude Code. Not affiliated with Anthropic.

Browse

  • Skills
  • MCP servers
  • Marketplaces
  • Weekly digest
  • Skill index
  • MCP index
  • Marketplace index

Site

  • About
  • Tools
  • Submit
  • Feedback
  • Privacy
  • llms.txt
  • Plugins reference

Maker

  • Snug
  • Agent Caffeine
  • knobs
  • Wax
  • Vectoys
  • mertduzgun.com
Crafted at
Skills/AI & Agent Building
telagod avatar

Indexing Code

telagod/code-abyss

Before your agent touches a file, this runs abyss CLI to show you what else depends on it. You get caller traces with confidence scores, hotspot metrics, coupled files that change together, and test coverage gaps. The hook auto-fires on edits so high-risk changes surface warnings before they ship. Works across Claude Code, Codex, Gemini, and others via shell access. The confidence tiering is smart: 1.0 for same-file calls down to 0.7 for ambiguous matches, so you know what's reliable versus a hint. If you've ever broken production because you didn't know a utility function had 500 transitive callers, this catches that.

GitHub stars
224
last updated
Jun 10, 2026
View on GitHubSave

Install

$ npx -y skills add telagod/code-abyss --skill indexing-code --agent claude-code

Installs into .claude/skills of the current project.

Files

代码关系图 · abyss

不是搜索工具,是代码的调用图 + 时间智能。通过 shell 调用 abyss CLI。

前置

进入项目时,检查并初始化索引:

command -v abyss >/dev/null && [ ! -f .code-abyss/index.db ] && abyss index

核心行为

改文件前:跑 abyss context

即将修改任何代码文件时,先获取该文件的完整上下文(不需要知道函数名):

abyss context <要修改的文件路径> --json

返回:该文件所有函数的外部调用方、依赖的类型和函数、热点评分、耦合文件。

根据返回结果:

  • 有 production callers:检查改动是否会破坏调用方,改完逐个同步
  • hotspot score > 5000:高风险文件,跑 abyss impact <func> --json 深入分析
  • impact risk > 7/10:跟用户确认方案后再改
  • 有 uncovered paths:提醒用户补测试
  • 有 coupled files:检查耦合文件是否需要同步修改

其他场景

场景命令
初识项目架构abyss map --json
追查 bug 来源abyss history <file> --symbol <func> --json
搜索代码(比 grep 好)abyss search "关键词" --json

输出说明

--json 输出结构化 JSON,agent 直接解析。不加 --json 输出人类可读文本。

context 输出关键字段

{
  "symbols_with_external_callers": [
    { "symbol": "SetError",
      "external_callers": [
        { "file": "handler.go", "line": 42, "caller": "HandleRequest",
          "confidence": 0.95, "is_test": false }
      ],
      "possible_callers": []
    }
  ],
  "dependencies": [{ "name": "Account", "file": "types.go", "kind": "type_ref" }],
  "hotspot": { "score": 5200, "changes_30d": 12, "complexity": 433 },
  "coupled_files": [{ "file": "gateway.go", "co_changes": 13, "coupling": "65%" }]
}
  • external_callers:confidence ≥ 0.7 的可信调用方,按解析档位标注(1.0 同文件 / 0.95 同包 / 0.9 import 限定 / 0.8 全局唯一)
  • possible_callers:confidence < 0.7 的歧义匹配——参考线索,不是事实,勿据此改调用方

impact 输出关键字段

{
  "direct_callers": 17,
  "transitive_callers": 521,
  "uncovered_paths": ["handler.go:DoSomething"],
  "risk_score": 8.5,
  "risk_factors": ["high blast radius", "319 paths without test coverage"]
}

CLI 速查

abyss index                           # 建索引(~5s)
abyss context <file> [--json]         # 文件完整上下文(改代码前用这个)
abyss callers <symbol> [--json]       # 谁调了这个函数(默认隐藏 confidence < 0.7)
abyss callers <symbol> --min-confidence 0   # 连歧义匹配一起看
abyss impact <symbol> [--json]        # 改了会影响什么(低置信边被排除时会在 risk_factors 标注)
abyss hook pre-edit                   # agent hook:stdin 读 tool JSON,增量刷新索引后输出警告
abyss hook post-edit                  # agent hook:编辑后增量刷新索引
abyss search "query" [--json]         # 搜索代码
abyss map [--json]                    # 项目热点+耦合
abyss history <file> [--symbol X]     # 变更历史
abyss stats                           # 索引统计

Hook 自动执行

Hook 注入按 host 分两条路径(hybrid 切割架构,2026-06-25 锁定):

claude / codex / gemini — 由 abyss CLI 的 attach 子命令负责(production 主入口,abyss v0.5.20+):

abyss attach claude     # → ~/.claude/settings.json
abyss attach codex      # → ~/.codex/config.toml(Codex 0.125+ 数组表)
abyss attach gemini     # → ~/.gemini/settings.json(SessionStart/BeforeTool/AfterTool)
abyss attach all        # 三平台一次完成

幂等,重跑覆盖旧 shape,不污染其它键。

二进制查找顺序:PATH → ~/.code-abyss/bin/abyss。两处都没有时 hook 静默停用,后装 abyss 即生效,无需重装。

v4.8.x → v4.9 deprecation 期变更

  • --with-hooks 对 claude/codex/gemini 仍写入 hook,但 install.js 打印 warning 引导改用 abyss attach <host>;v5.0 移除该路径(openclaw/pi/hermes 的 --with-hooks 永久保留并改造为 spawn install-hooks.sh)
  • --with-abyss 已移除(Agent OS v5.1)。请用 curl -fsSL https://raw.githubusercontent.com/telagod/abyss/main/install.sh | bash;claude/codex/gemini graph hooks 用 abyss attach <host>
  • --with-mcp 注册 abyss MCP 进入 deprecation,引导用户改用 abyss mcp 客户端自配;v5.0 移除

openclaw / pi / hermes — 由 code-abyss npm 包负责(abyss CLI 不接管这三平台,见 abyss src/attach/mod.rs 注释):

npx code-abyss --target openclaw --with-hooks   # 自动 spawn install-hooks.sh
npx code-abyss --target pi       --with-hooks
npx code-abyss --target hermes   --with-hooks

或脱离安装器直接跑脚本:

bash skills/indexing-code/hooks/common/install-hooks.sh auto   # 自动检测平台

自动检测平台并注入对应 hook 配置(幂等,JSON 合并用 node):

平台Hook 事件配置位置
Claude CodePreToolUse(Edit|Write).claude/settings.json
Codex CLIPreToolUse(Bash|shell|apply_patch|Edit|Write)~/.codex/config.toml
Gemini CLIBeforeTool(write_file|replace)~/.gemini/settings.json
Pi Agenttool_call(edit_file|write_file)~/.pi/agent/settings.json
Hermespre_tool_call~/.hermes/config.yaml 或 plugin
OpenClawbefore_tool_callplugin api.on()

统一入口是 abyss hook pre-edit(shell 脚本只是带存在性守卫的薄壳):自动识别各平台 stdin JSON 形状、增量刷新索引(警告反映文件当前状态而非旧索引)、输出生产调用方 / 歧义引用 / 热点警告。编辑后可挂 abyss hook post-edit 保持索引新鲜。agent 无需手动调用。

SKILL.md on GitHub

Sponsors

SnugThe clipboard manager you and your agent can use, safelyAgent CaffeineClose your lid, come back to finished workWaxBlock anything with supervision, without erasing your iPhoneOpen StepsSponsoredFree and open-source skills that make AI coding agents easier to understand, verify, and control.

Details

Repository
github.com/telagod/code-abyss
Categories
AI & Agent Building, CLI & Terminal
License
MIT
First seen
Jun 11, 2026

More from telagod/code-abyss

All 30
  • Operating Kicad Eda
  • Orchestrating Adversarial Reviews
  • Processing Docx
  • Processing Pdfs
  • Provisioning Infrastructure
  • Reducing Aigc Detection
  • Securing Cloud And Supply Chain
  • Securing Systems
  • Shipping Changes
  • Verifying Modules
  • Analyzing Changes
  • Analyzing Security
  • Analyzing Spreadsheets
  • Applying Ui Design System
  • Architecting Security
  • Automating Devops
  • Building Agent Systems
  • Checking Code Quality
  • Creating Presentations
  • Cultivating Personas
  • Cultivating Skills
  • Defending Applications
  • Designing Architectures
  • Designing Hardware Products

Recommended

More AI & Agent Building
1telagod avataroperating-kicad-edatelagod/code-abyssKiCad EDA orchestration via kicad-mcp MCP server. Routes 17 tools for schematic creation, PCB layout, autorouting, DRC, and Gerber export. Enforces serialized P0installs
2ThinkInAIXYZ avataradd-providerThinkInAIXYZ/deepchatAdd a DeepChat LLM provider through explicit reviewed source changes. Use when a developer asks Codex to add a provider, provider profile, upstream provider con0installs
3thinkinaixyz avatarcua-driverthinkinaixyz/deepchatDrive native macOS apps through DeepChat's plugin-provided Computer Use MCP tools. Use when the user asks to operate, inspect, automate, or perform a GUI task i0installs
4thinkinaixyz avatarfeishu-toolsthinkinaixyz/deepchatUse the Feishu/Lark plugin MCP tools for Feishu documents, spreadsheets, knowledge content, and other matching workspace operations.0installs
5ThinkInAIXYZ avatarmemory-managementThinkInAIXYZ/deepchatGuide the agent to recall, remember, and route durable learning into Memory, Skills, Scheduled Tasks, or Tape.0installs
6tzachbon avatardelegation-principletzachbon/smart-ralphCore principle that the main agent is a coordinator, not an implementer. All work must be delegated to subagents.0installs