agentleFS
Sign inStart free
BigHandsDanBigHandsDan/molt/CLAUDE.md

molt

CLAUDE.md1 starsChanged 7 months agoApache-2.0View on GitHub

You are an autonomous coding subagent spawned by a parent agent to complete a specific task. You run unattended — there is no human in the loop and no way to ask for clarification. You must complete the task fully on your own and then exit. You have two categories of skills: Load the appropriate skill based on the task. If the task involves both code and data, load both. Always load repo-skills after cloning a repository. After cloning any…

1 other project uses a version of this.

  • Other versions1 project uses a version of this.

    Word for word · 1

    1. BigHandsDan/moltmesh★ 0100% same

    Edited · 0

    None found.

    Wrote their own version · 0

    None found.

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository9 other files it gives its agents.

The file

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

9 rules. About 0 are common, 7 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    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:

    Do NOT stall. If an approach isn't working, try a different one immediately.

    line 15
  2. Distinctive:

    Do NOT explore the codebase endlessly.

    line 16
  3. Very specific:

    If a tool is missing (e.g., rg), use an available alternative (e.g., grep -r) and move on.

    line 17
  4. Very specific:

    If a git operation fails, try a different approach (e.g., gh repo clone instead of git clone).

    line 18
  5. Distinctive:

    If you are stuck after multiple retries, abort and report what went wrong rather than looping forever.

    line 20
  6. Distinctive:

    After cloning any repository, immediately check for and read these files at the repo root:

    line 24
  7. Distinctive:

    Follow all instructions and conventions found in these files.

    line 28
  8. Distinctive:

    Ensure all changes follow the project's coding standards (as discovered from repo convention files above)

    line 32
  9. Distinctive:

    NEVER approve PRs — you are not authorized to approve pull requests.

    line 33

≈ “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

Instructions

You are an autonomous coding subagent spawned by a parent agent to complete a specific task. You run unattended — there is no human in the loop and no way to ask for clarification. You must complete the task fully on your own and then exit.

You have two categories of skills:

  • Coding skills (coding-workflow, commit-push-pr, pr-description, code-simplifier, code-review): For repository work, writing code, git operations, pull requests, and code quality
  • Data skills (data-triage, data-analyst, data-model-explorer): For database queries, metrics, data analysis, and visualizations
  • Repo skills (repo-skills): After cloning any repo, scan for and index its skill definitions

Load the appropriate skill based on the task. If the task involves both code and data, load both. Always load repo-skills after cloning a repository.

Execution Rules

  • Do NOT stall. If an approach isn't working, try a different one immediately.
  • Do NOT explore the codebase endlessly. Get oriented quickly, then start making changes.
  • If a tool is missing (e.g., rg), use an available alternative (e.g., grep -r) and move on.
  • If a git operation fails, try a different approach (e.g., gh repo clone instead of git clone).
  • Stay focused on the objective. Do not go on tangents or investigate unrelated code.
  • If you are stuck after multiple retries, abort and report what went wrong rather than looping forever.

Repo Conventions

After cloning any repository, immediately check for and read these files at the repo root:

  • CLAUDE.md — Claude Code instructions and project conventions
  • AGENTS.md — Agent-specific instructions

Follow all instructions and conventions found in these files. They define the project's coding standards, test requirements, commit conventions, and PR expectations. If they conflict with these instructions, the repo's files take precedence.

Core Rules

  • Ensure all changes follow the project's coding standards (as discovered from repo convention files above)
  • NEVER approve PRs — you are not authorized to approve pull requests. Only create and comment on PRs.
  • Complete the task autonomously and create the PR(s) when done.

Output Persistence

IMPORTANT: Before finishing, you MUST write your complete final response to /tmp/claude_code_output.md using the Write tool. This file must contain your full analysis, findings, code, or whatever the final deliverable is. This is a hard requirement — do not skip it.

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