skills/developer-tools-integrations/agents-md-improver/SKILL.md
Audit and improve Codex AGENTS.md guidance files and companion code_map.md navigation maps in repositories. Use when the user asks to check, audit, update, optimize, or fix AGENTS.md files; asks for Codex project guidance maintenance; mentions nested AGENTS.md conflicts, code maps, stale commands, scoped instructions, sandbox or approval boundaries; or says "优化 AGENTS.md", "审计 AGENTS.md", "检查 nested AGENTS.md", "更新 Codex 项目指导", or "生成 code_map.md".
npx skillsauth add bahayonghang/my-claude-code-settings agents-md-improverInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Audit and improve Codex AGENTS.md guidance files and companion code_map.md navigation maps so future Codex CLI, Codex App, and native subagent sessions receive concise, accurate, scoped project instructions and fast code search entry points.
Default mode is report-first. Output a quality report and proposed diff before writing. If the user explicitly asks to implement an approved plan, continue directly to targeted edits and verification.
AGENTS.md file governs the directory that contains it and every descendant directory.AGENTS.md adds or overrides guidance for its subtree.AGENTS.md content.AGENTS.md files are project guidance. User-level ~/.codex/AGENTS.md is global preference guidance and should not be edited unless explicitly requested.AGENTS.md carries durable behavioral constraints, commands, and safety rules. code_map.md carries navigational structure, search anchors, entry points, and generated/ignored directory notes.AGENTS.md should explicitly name the relative code_map.md path agents must read before broad grep or repo-wide search, for example See ./code_map.md before broad grep or For this subtree, start with platforms/codex/code_map.md.<!-- OMX:RUNTIME:START --> ... <!-- OMX:RUNTIME:END --> and <!-- OMX:TEAM:WORKER:START --> ... <!-- OMX:TEAM:WORKER:END -->.Find scoped guidance files:
# POSIX shells
find . \( -name AGENTS.md -o -name code_map.md \) \
-not -path './.git/*' \
-not -path './node_modules/*' \
-not -path './target/*' \
-not -path './dist/*' \
-not -path './build/*' \
-not -path './.omx/state/*'
# PowerShell
Get-ChildItem -Recurse -Force -Include AGENTS.md,code_map.md |
Where-Object { $_.FullName -notmatch '\\.git|node_modules|target|dist|build|\\.omx\\state' } |
Select-Object -ExpandProperty FullName
Exclude generated, vendored, dependency, cache, and build-output directories from guidance creation scans, including .git/, node_modules/, target/, dist/, build/, .omx/state/, vendor/, generated docs output, coverage output, and language-specific package caches.
Discover candidate directories for new nested AGENTS.md plus local code_map.md before proposing writes. Score only real source subtrees that show one or more of:
package.json, Cargo.toml, pyproject.toml, go.mod, Makefile, justfile, or CI/workflow fragmentsAlso note, but do not edit by default:
~/.codex/AGENTS.md
.codex/agents/
.codex/skills/
Classify each file:
| Type | Location | Purpose |
|---|---|---|
| root guidance | ./AGENTS.md | repo-wide commands, architecture, gates, safety boundaries |
| nested scoped guidance | ./<subtree>/AGENTS.md | local commands, ownership, generated files, conventions |
| root code map | ./code_map.md | repo navigation, top-level routing, search anchors, ignored/generated paths |
| nested code map | ./<subtree>/code_map.md | subtree entry points, internal routing, upstream/downstream boundaries |
| user global guidance | ~/.codex/AGENTS.md | user-wide preferences, outside repo scope |
| generated/runtime guidance | .omx/.../AGENTS.md or similar | runtime state; usually read-only/no-edit |
For every repo guidance file, verify claims against the repository:
package.json, justfile, Cargo.toml, pyproject.toml, Makefile, CI filescode_map.md files, map pointers in AGENTS.md, and whether map content is navigational rather than behavioral.codex/skills, .codex/agents, AGENTS.md scope rules, sandbox/approval notesUse references/quality-criteria.md for detailed scoring, including the nested AGENTS.md creation scorecard.
Quick checklist:
| Criterion | Weight | Check | |---|---:|---| | scope and override clarity | 20 | file explains what subtree it governs and how it relates to parent guidance | | executable commands and gates | 20 | build/test/lint/typecheck commands are real and scoped | | architecture and ownership | 15 | enough map to route future edits without restating obvious code | | safety and permissions | 15 | sandbox, approvals, secrets, destructive operations, external services are clear | | Codex workflow fit | 15 | skills/subagents/plugins/OMX guidance is accurate and not overpromised | | conciseness and currency | 15 | current, dense, non-duplicative, no stale file paths |
For each candidate nested subtree, record:
>=60), candidate only (40-59), or do not create (<40)code_map.md path and whether a local nested map should be createdGrades:
Always provide this report before edits unless the user already approved an implementation plan.
## AGENTS.md Quality Report
### Summary
- Files found: X
- Root guidance: present/missing
- Root code map: present/missing
- Nested scoped files: X
- Nested code maps: X
- Average score: X/100
- Files needing update: X
- Candidate nested guidance dirs: X create / X candidate-only / X skipped
### Scope Map
| File | Governs | Parent guidance | Notes |
|---|---|---|---|
| `AGENTS.md` | repo root | none | ... |
| `packages/api/AGENTS.md` | `packages/api/**` | root | ... |
### Code Map Coverage
| Map | Covers | Referenced by | Notes |
|---|---|---|---|
| `code_map.md` | repo root | `AGENTS.md` | ... |
### Nested Guidance Candidates
| Directory | Score | Decision | Evidence |
|---|---:|---|---|
| `packages/api/` | 75 | create `packages/api/AGENTS.md` + `packages/api/code_map.md` | independent tests, deploy boundary |
### File-by-File Assessment
#### 1. `AGENTS.md`
**Score: XX/100 (Grade: X)**
| Criterion | Score | Notes |
|---|---:|---|
| scope and override clarity | X/20 | ... |
| executable commands and gates | X/20 | ... |
| architecture and ownership | X/15 | ... |
| safety and permissions | X/15 | ... |
| Codex workflow fit | X/15 | ... |
| conciseness and currency | X/15 | ... |
**Issues**
- ...
**Proposed changes**
- ...
When approved or already authorized by a plan:
code_map.md; keep behavioral rules, commands, and safety constraints in AGENTS.md.AGENTS.md instead of duplicating it everywhere.AGENTS.md names the exact relative code_map.md path agents should read first.Run the smallest checks that prove the edits:
git diff --checkAGENTS.md files reference an explicit relative code_map.md pathIf a documented full gate is expensive, state whether it was run or why it was not.
references/quality-criteria.md — scoring rubric and red flagsreferences/templates.md — root, monorepo package, frontend/backend/docs templatesreferences/update-guidelines.md — what to add, avoid, and preserveAGENTS.md missing commands required by CI or local developmentAGENTS.md missing an explicit ./code_map.md pointer when a root map exists or should existAGENTS.md contradicts parent guidance without saying whyAGENTS.md only says "read the code map" without naming the relative map pathAGENTS.md bloated with directory index content that belongs in code_map.md## AGENTS.md Update Summary
### Files changed
- `AGENTS.md` — ...
- `packages/api/AGENTS.md` — ...
- `code_map.md` — ...
- `packages/api/code_map.md` — ...
### What improved
- scope/override clarity
- command/gate accuracy
- safety boundaries
- map-first search flow with explicit relative `code_map.md` paths
### Verification
- `git diff --check` — passed
- `<targeted command>` — passed/failed/skipped with reason
### Remaining risks
- ...
development
Turn vague or complex Codex tasks into strong `/goal` commands with outcome, verification, constraints, boundaries, iteration policy, completion evidence, and pause/block conditions. Use when the user asks for Codex goal instructions, Goal 指令, 目标指令, `/goal` prompts, 中文 Goal 模板, plan-to-goal interviews, success criteria, verification commands, or bounded agent work definitions.
tools
Write, debug, and validate ast-grep structural code search rules. Use this skill when the user needs syntax-aware code search, AST pattern matching, structural refactor discovery, language-construct queries, or searches that plain text tools like rg can miss, such as finding functions with particular descendants, calls inside specific contexts, missing error handling, React hook shapes, decorators, or other Tree-sitter-backed code structures.
development
Use when the user asks to ground an ambitious proposal, avoid over-grand designs, make a bold direction executable, pressure-test feasibility, prevent "too much vision and too little landing", or turn a strategy/refactor/product idea into the smallest verifiable first move with stop rules. Trigger for requests such as 落地, 先落地, 别太飘, 收一收, 可执行, 可验证, 止损, and for follow-ups after geju-style big-picture thinking. Do not trigger for ordinary code review or implementation unless the user explicitly asks to ground or shrink the plan first.
development
Use when the user explicitly asks to think bigger, open up the design space, challenge conservative design, avoid over-indexing on backward compatibility, escape local-detail fixation, or make a bold high-level product or architecture direction call. Use for strategic reframing, not for ordinary code review, PRD writing, implementation planning, or adversarial risk review.