agentleFS
Sign inStart free
MiviaLabsMiviaLabs/mivia-agentkit/CLAUDE.md

mivia-agentkit

CLAUDE.md2 starsChanged 4 months agoMITView on GitHub

Root AGENTS.md is canonical. Read it first, then read .ai/INDEX.md and the relevant .ai/rules/*.md files for the task. Claude-specific notes: Claude hook mapping: Claude hook payloads arrive as JSON on stdin. Handlers must inspect event name, tool name and arguments for PreToolUse and PermissionRequest, prompt text for UserPromptSubmit, and stop-state fields for Stop; they must return a scrubbed decision without persisting raw prompts, raw tool input containing secrets, or raw model output. Do not add policy here that conflicts with…

The file

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

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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
  1. Distinctive:

    Before editing files, state the intended edits briefly.

    line 7
  2. Distinctive:

    Run the relevant tests or validation commands after changes.

    line 8
  3. Very specific:

    Keep .claude/settings.json as the project settings and hook reference.

    line 9
  4. Very specific:

    Use .claude/skills/ for Claude Code skill adapters.

    line 10
  5. Distinctive:

    Do not add policy here that conflicts with AGENTS.md.

    line 21

≈ “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

Claude Code Adapter

Root AGENTS.md is canonical. Read it first, then read .ai/INDEX.md and the relevant .ai/rules/*.md files for the task.

Claude-specific notes:

  • Before editing files, state the intended edits briefly. After editing, show or summarize the diff before finalizing.
  • Run the relevant tests or validation commands after changes. If tests cannot run because no Go module or code exists yet, say that explicitly.
  • Keep .claude/settings.json as the project settings and hook reference. Current hooks delegate through scripts/run_agent_hook_guard.sh, which applies the repo guard before any future mivia-agent handler.
  • Use .claude/skills/ for Claude Code skill adapters. Canonical project workflows live under .ai/skills/.

Claude hook mapping:

  • UserPromptSubmit -> scripts/run_agent_hook_guard.sh claude user-prompt-submit
  • PreToolUse -> scripts/run_agent_hook_guard.sh claude pre-tool-use
  • PermissionRequest -> scripts/run_agent_hook_guard.sh claude permission-request
  • Stop -> scripts/run_agent_hook_guard.sh claude stop

Claude hook payloads arrive as JSON on stdin. Handlers must inspect event name, tool name and arguments for PreToolUse and PermissionRequest, prompt text for UserPromptSubmit, and stop-state fields for Stop; they must return a scrubbed decision without persisting raw prompts, raw tool input containing secrets, or raw model output.

Do not add policy here that conflicts with AGENTS.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