agentleFS
Sign inStart free
chenson42chenson42/stackkeel/CLAUDE.md

stackkeel

CLAUDE.md1 starsChanged 51 days agoMITView on GitHub

Everything binding lives in AGENTS.md (imported above). The notes below only cover tooling that exists for Claude Code specifically. - Hooks are wired in .claude/settings.json: SessionStart runs the kit-check banner and kit:status digest; PreToolUse gates enforce work-log-before-code and personalize-before-edit; a Bash gate blocks git push without a fresh pre-push stamp. These are the fast-feedback layer — the same rules are enforced tool-agnostically by git hooks and CI, so never treat a missing hook as permission. - Agent roster lives in…

  • Commits and pushes

The file

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

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Every agent pins effort: high except deployment-engineer (medium).

    line 22

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.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
CLAUDE.md

@AGENTS.md

Claude-specific notes

Everything binding lives in AGENTS.md (imported above). The notes below only cover tooling that exists for Claude Code specifically.

  • Hooks are wired in .claude/settings.json: SessionStart runs the kit-check banner and kit:status digest; PreToolUse gates enforce work-log-before-code and personalize-before-edit; a Bash gate blocks git push without a fresh pre-push stamp. These are the fast-feedback layer — the same rules are enforced tool-agnostically by git hooks and CI, so never treat a missing hook as permission.
  • Agent roster lives in .claude/agents/ — one file per pipeline role (see AGENTS.md → Development Pipeline). Judgment agents (analyst, architect, qa) are tool-restricted to read-only.
  • Model tiering is set per agent in frontmatter (model: + effort:), rationale in docs/decisions.md → DECISION-008 (which supersedes DECISION-007's assignment). opus for invariant rulings, migrations, and the last gate before ship (architect, database-admin, qa); sonnet for everything else — work that is contract-driven, lands in a work-log the next phase re-derives, and is re-verified downstream. No agent runs fable: at effort: high its cost was out of proportion to the judgment it bought. Every agent pins effort: high except deployment-engineer (medium). Override per invocation with the Agent tool's model parameter when a task is unusually hard or unusually routine.
  • Skills live in .claude/skills/ and are invocable as slash commands (/new-feature, /pre-push, /personalize, /upstream-sync, …). They follow the cross-tool SKILL.md standard, so treat them as the canonical procedure definitions, not Claude-only helpers.

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