syncwinsyncwin/ai-extender/AGENTS.md

ai-extender

AGENTS.md0 starsChanged 39 days agoMITView on GitHub

AI Extender for Claude: plans, builds, checks and packages Claude skills, plugins, connectors and agents. Structure: skills/ai-extender (router) and claude-planner|developer|maintainer|reviewer|packager, agents/ (comparator, grader), hooks/hooks.json, evals/, .github/ (CI).

Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository9 other files it gives its agents.
- skills/claude-developer/references/agents.mdAGENTS.md
- .claude/CLAUDE.mdCLAUDE.md
- ai-extenderSkill
- claude-developerSkill
- claude-maintainerSkill
- claude-packagerSkill
- claude-plannerSkill
- claude-reviewerSkill
- prompt-builderSkill

The file

We split this AGENTS.md into the rules it gives an agent

7 rules. About 1 is common, 4 are distinctive, and 2 are very specific to this project.

≈1
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific
could be automatic: a setting could enforce it

Distinctive:
Read the skill or script you change, plus its neighbours.
line 16
Very specific:
Update CHANGELOG.md for behavior changes.
line 18
Distinctive:
Run the closest check and the full gate before committing.
line 21
Very specific:
Follow neighbouring files.
line 22
Distinctive:
No commits, pushes or PRs unless asked.
line 24
Distinctive:
No new dependencies without asking (scripts stay on the Python standard library).
line 25
Common:
Never commit secrets. Never pick names or slugs without user confirmation.
line 26

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

AGENTS.md

ai-extender agent guide

AI Extender for Claude: plans, builds, checks and packages Claude skills, plugins, connectors and agents.

Structure: skills/ai-extender (router) and claude-planner|developer|maintainer|reviewer|packager, agents/ (comparator, grader), hooks/hooks.json, evals/, .github/ (CI).

Commands

Self-test (must pass): python skills/claude-reviewer/scripts/selftest.py
Strict validation (must pass): python skills/claude-reviewer/scripts/validate_extension.py . --strict --target directory --require-meta author,company
Secret scan: python skills/claude-reviewer/scripts/scan_secrets.py
Version bump: skills/claude-maintainer/scripts/bump_version.py; package: skills/claude-packager/scripts/package_extension.py
Validate: claude plugin validate . --strict
Evals (real model calls): claude plugin eval . --trust-plugin --ablation none --scaffold --allow-tools Read Glob Grep Skill -j 4 --no-publish. Rebuild cases with python A:\Automation\plugin-evals\regen_evals.py <plugin> <router> <fixture ids>. Write results outside the repo (D:\SyncWin\AI Outputs\<plugin>\eval-results); the packager includes repo files.

Workflow

Read the skill or script you change, plus its neighbours.
Make the smallest change; run the closest check, then the full gate.
Update CHANGELOG.md for behavior changes; log ideas in IMPROVEMENTS.md.

Rules

Run the closest check and the full gate before committing. Never delete or weaken tests or evals. Report failed, skipped or timed-out runs honestly; NOT RUN is never a pass.
Follow neighbouring files. Keep each SKILL.md under 500 lines; move detail into references/.
On release, bump version in .claude-plugin/plugin.json and every skill's metadata.version together; add a CHANGELOG.md entry per behavior change.
No commits, pushes or PRs unless asked. Work on a branch and open a PR; never push to main.
No new dependencies without asking (scripts stay on the Python standard library).
Never commit secrets. Never pick names or slugs without user confirmation.
Pin any GitHub Action to a full commit SHA with the version in a comment; give each job least permissions.
A platform fact needs its official page and the date checked. Keep private data (keys, client names, internal URLs) out of every file.
Plugin versions 1.0.0 and 1.1.0 are both kept (user decision, 4 Nov). The public-review syncwin marketplace entry is not changed.

Model routing

Opus plans, decides, writes self-contained briefs with a report word limit, and reviews every result. Haiku for search, reading and mechanical edits. Sonnet for coding, tests and multi-step work. Do 1-2 tool calls inline.

Docs

README.md, CONTRIBUTING.md, CHANGELOG.md, SECURITY.md; ideas and feedback in IMPROVEMENTS.md.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free