agentleFS
CodeAlive-AICodeAlive-AI/ai-driven-development/AGENTS.md

ai-driven-development

AGENTS.md169 starsChanged 56 days agoMITView on GitHub

This repo is a single-plugin marketplace and a cross-agent skill collection in one. The same skills/ directory at the repo root is read by both npx skills add (the cross-agent CLI) and Claude Code's plugin install (/plugin marketplace add + /plugin install …@ai-driven-development). The plugin sees the repo root as itself via source: "./" in marketplace.json — no nesting, no symlinks, no duplication. When the user asks to commit or push without naming a target branch, commit and push directly…

  • Commits and pushes

The file

Show its rules and text

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

14 rules. About 0 are common, 4 are distinctive, and 10 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 10

    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
  1. Distinctive:

    When the user asks to commit or push without naming a target branch, commit and push directly to main.

    line 7
  2. Distinctive:

    Update the relevant section table in README.md

    line 46
  3. Very specific:

    Update the skill's own SKILL.md (agent-facing) and README.md (human-facing, optional)

    line 47
  4. Very specific:

    Update .claude-plugin/plugin.json and .claude-plugin/marketplace.json versions

    line 48
  5. Very specific:

    Do not create or commit per-skill snapshots or edit-history artifacts, including .skill_snapshots/, .snapshots/, and .skill_edit_log.jsonl.

    line 52
  6. Very specific:

    When skill/hook/plugin files change:

    line 67
  7. Very specific:

    Create and push tag: git tag -a vX.Y.Z -m "Version X.Y.Z" && git push origin vX.Y.Z

    line 71
  8. Very specific:

    Create GitHub release: gh release create vX.Y.Z --title "vX.Y.Z — Title" --notes "Release notes"

    line 72
  9. Very specific:

    Create skills/<skill-name>/SKILL.md with YAML frontmatter (name, description).

    line 95
  10. Very specific:

    Add optional README.md, references/, scripts/, assets/ as needed.

    line 96
  11. Distinctive:

    Update the relevant section table in the root README.md.

    line 97
  12. Very specific:

    Create hooks/<hook-name>/ with the hook implementation, install.sh, and README.md.

    line 103
  13. Very specific:

    If the hook ships pre-built binaries, add a release flow (see hooks/balanced-safety-hooks/ as the canonical example: cross-platform Go …

    line 104
  14. Distinctive:

    Update the Hooks section in the root README.md.

    line 105

≈ “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-Driven Development — Development Guide

This repo is a single-plugin marketplace and a cross-agent skill collection in one. The same skills/ directory at the repo root is read by both npx skills add (the cross-agent CLI) and Claude Code's plugin install (/plugin marketplace add + /plugin install …@ai-driven-development). The plugin sees the repo root as itself via source: "./" in marketplace.json — no nesting, no symlinks, no duplication.

Git publishing defaults

When the user asks to commit or push without naming a target branch, commit and push directly to main. If the current branch is main, stay on it; do not create a feature branch by default. Use another branch only when the user explicitly requests one.

When to create tags and releases

Only create git tags and GitHub releases when skill, hook, or plugin files change.

Requires a new tag/release

  • skills/*/ — any skill file changes (SKILL.md, scripts, references, assets)
  • hooks/*/ — any hook source changes (Go code, install scripts, hook configs)
  • .claude-plugin/plugin.json — plugin manifest changes
  • .claude-plugin/marketplace.json — marketplace catalogue changes
  • LICENSE — licence changes

Examples:

  • Adding a new skill or hook
  • Updating skill instructions in SKILL.md
  • Modifying skill scripts
  • Changing plugin metadata or version

Does NOT require a new tag/release

Documentation-only changes don't need tagging:

  • README.md — documentation and use-case updates
  • AGENTS.md and the CLAUDE.md import shim — repository instructions
  • Commit messages
  • GitHub-specific files (.github/*)

Rationale: users install specific commits via SHA. Documentation updates don't affect functionality, so they don't need version bumps. This keeps the release history clean.

README maintenance

The repo ships English-only. When you add or remove a skill, or change a skill description:

  • Update the relevant section table in README.md
  • Update the skill's own SKILL.md (agent-facing) and README.md (human-facing, optional)
  • Update .claude-plugin/plugin.json and .claude-plugin/marketplace.json versions

Generated skill artifacts

Do not create or commit per-skill snapshots or edit-history artifacts, including .skill_snapshots/, .snapshots/, and .skill_edit_log.jsonl. Git history is the sole record of skill changes. These generated artifacts are ignored by the root .gitignore and must not be force-added.

Versioning

Follow semver:

  • MAJOR (x.0.0) — breaking changes to skill interfaces, removals, layout overhauls
  • MINOR (X.x.0) — new skills, new hooks, backward-compatible features
  • PATCH (X.X.x) — bug fixes, prompt tweaks, doc fixes that ship in skills

Release process

When skill/hook/plugin files change:

  1. Bump version in .claude-plugin/plugin.json AND .claude-plugin/marketplace.json (keep them in sync).
  2. Commit changes.
  3. Create and push tag: git tag -a vX.Y.Z -m "Version X.Y.Z" && git push origin vX.Y.Z
  4. Create GitHub release: gh release create vX.Y.Z --title "vX.Y.Z — Title" --notes "Release notes"

The bash-guard hook ships its own pre-built binary release with a separate tag (bash-guard-vX.Y.Z) — see hooks/balanced-safety-hooks/ for that release flow.

Repository structure

ai-driven-development/
├── .claude-plugin/
│   ├── marketplace.json    ← single-plugin marketplace, source: "./"
│   └── plugin.json
├── skills/                  ← canonical Agent Skills layout (npx skills add)
│   └── <skill-name>/SKILL.md (+ optional README.md, references/, scripts/, assets/)
├── hooks/
│   └── <hook-name>/         ← Claude Code hooks (Go binary + install scripts)
├── README.md
├── AGENTS.md               ← canonical repository instructions
├── CLAUDE.md               ← imports AGENTS.md for Claude Code
└── LICENSE

Adding a new skill

  1. Create skills/<skill-name>/SKILL.md with YAML frontmatter (name, description).
  2. Add optional README.md, references/, scripts/, assets/ as needed.
  3. Update the relevant section table in the root README.md.
  4. Bump version in both .claude-plugin/*.json files (minor bump for new skill).
  5. Commit, tag, release.

Adding a new hook

  1. Create hooks/<hook-name>/ with the hook implementation, install.sh, and README.md.
  2. If the hook ships pre-built binaries, add a release flow (see hooks/balanced-safety-hooks/ as the canonical example: cross-platform Go build via make build-all, GitHub release with SHA256SUMS, install-prebuilt.sh that pins by tag).
  3. Update the Hooks section in the root README.md.
  4. Bump version in both .claude-plugin/*.json files.
  5. Commit, tag, release.

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.