
agent-ready
Make a codebase agent-ready with progressive-disclosure documentation, domain context, regression-aware quality gates, and stack-specific skill recommendations. Uses AGENTS.md directly with Claude Code 2.1.277+ without requiring a CLAUDE.md symlink.
- version
- 2026.10.1
- GitHub stars
- 72
Install
/plugin install agent-ready@dgalarza-agent-skillsRun it inside Claude Code after adding the marketplace with /plugin marketplace add dgalarza/claude-code-workflows.
Contents
Discovered from sourceAgents 1
agent-ready
Make a codebase agent-ready by scaffolding AGENTS.md, ARCHITECTURE.md, and a docs/ structure that follows progressive disclosure, installing a regression-aware quality gate, and recommending project-local skills for the detected stack.
This is the remediation companion to codebase readiness. Codebase readiness scores the repository. Agent-ready closes the documentation and quality-gate gaps.
Start at the landing page: agent-ready.
Install
From this repository, after the marketplace is added:
/plugin marketplace add dgalarza/agent-skills
/plugin install agent-ready@dgalarza-agent-skills
npx skills add dgalarza/agent-skills --skill agent-ready
These commands are the GitHub install path. The landing page is the supported way to get the skill.
Modes
| Mode | What it does | Example prompt |
|---|---|---|
| scaffold | Full setup: docs/ structure, ARCHITECTURE.md, AGENTS.md, documentation check, quality gate | "Make this codebase agent-ready" |
| architecture | Generate ARCHITECTURE.md from the actual codebase | "Create an ARCHITECTURE.md" |
| agents-md | Create or refactor AGENTS.md for progressive disclosure | "Set up AGENTS.md" |
| quality-gates | Install a regression-aware quality gate: native complexity, duplication, and dead-code checks, a reviewed baseline, merge-base-aware CI, docs, and tests | "Set up quality gates" |
| migrate | Upgrade a legacy agent-ready scaffold to the current domain-context, ADR, and documentation-check contract | "Migrate our agent-ready docs" |
| audit | Check existing agent-readiness artifacts and the quality gate for staleness, coherence, and governance | "Are my agent docs up to date?" |
Quality gates
Documentation tells an agent what good looks like. A quality gate stops it from shipping the opposite. The quality-gates mode installs a regression-aware gate: legacy debt stays in a baseline, and any change that adds complexity, duplication, or dead code — or makes a baselined finding worse — fails CI.
| Piece | Detail |
|---|---|
| Checks | The language's native tools. Native baseline or diff modes are used where they exist; otherwise a stdlib engine (assets/quality-gate.py) fingerprints findings so line-number churn does not look like new debt |
| Commands | report / check / baseline --prune, identical locally and in CI |
| Baseline | Created only with a written --reason and a human --approve --reviewed-by. check fails while it is unreviewed. Refused in CI. Stale entries fail until pruned |
| CI | Merge-base-aware job that annotates findings on the pull request diff |
| Docs | docs/guides/quality-gates.md plus Definition of Done directives in AGENTS.md |
| Tests | A self-test proving a clean tree passes, synthetic debt fails, and stale entries are pruned |
Agent instructions
The plugin generates AGENTS.md as the shared instruction file. Claude Code reads AGENTS.md directly starting with version 2.1.277, so do not add a CLAUDE.md symlink. Preserve an existing CLAUDE.md. If both files exist and disagree, say so.
The skill source is skills/agent-ready/. This plugin directory is a thin manifest; skills/agent-ready here symlinks to that canonical skill.
Recommended workflow
- Score the repo with codebase readiness.
- Run agent-ready to fix documentation and structure.
- If the Gate Maturity Level is L0-L2, run agent-ready in quality-gates mode.
- Re-run the assessment to measure the change.
If AGENT_READY_ASSESSMENT.md exists, agent-ready reads it and suggests which mode to run first.
Want help beyond documentation?
Built by Damian Galarza.
A Foundation Sprint is two weeks on the highest-leverage problem in the AI stack, followed by a Production AI retainer if the work should continue.
Sponsors
Details
- Marketplace
- dgalarza/claude-code-workflows
- Source
- plugins/agent-ready
- Category
- Community