agentleFS
Sign inStart free
VKambulovVKambulov/research-mode/AGENTS.md

research-mode

AGENTS.md4 starsChanged 5 months agoApache-2.0View on GitHub

This file is for coding agents and maintainers working on this repository. Human-facing project documentation starts at README.md. Detailed guides live under docs/, with repository-level files such as RELEASE_NOTES.md, RELEASING.md, CONTRIBUTING.md, ROADMAP.md, and SECURITY.md kept at the root. - Keep human documentation useful without requiring private workspace context. - Put operational instructions for OpenClaw runtime agents in SKILL.md. - Put repository-maintenance guidance for coding agents in this file. - Do not add private paths, chat ids, cron ids, tokens, webhook…

  • 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 repositoryOne other file it gives its agents.

The file

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

10 rules. About 0 are common, 7 are distinctive, and 3 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.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep human documentation useful without requiring private workspace context.

    line 11
  2. Very specific:

    Put operational instructions for OpenClaw runtime agents in SKILL.md.

    line 12
  3. Distinctive:

    Put repository-maintenance guidance for coding agents in this file.

    line 13
  4. Distinctive:

    Do not add private paths, chat ids, cron ids, tokens, webhook URLs, personal notes, or generated research artifacts to public examples.

    line 14
  5. Distinctive:

    Do not mix hidden prompts or agent-only instructions into human-facing docs.

    line 16
  6. Very specific:

    Read SKILL.md and the relevant helper modules under scripts/.

    line 20
  7. Distinctive:

    Keep task state and artifacts task-local and path-contained.

    line 23
  8. Very specific:

    Keep awaiting_review separate from delivered/completed state.

    line 24
  9. Distinctive:

    Keep finalization evidence explicit before a worker marks a result reviewable.

    line 25
  10. Distinctive:

    Run the release gate from the repository root after meaningful changes:

    line 29

≈ “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

Agent Notes

This file is for coding agents and maintainers working on this repository. Human-facing project documentation starts at README.md. Detailed guides live under docs/, with repository-level files such as RELEASE_NOTES.md, RELEASING.md, CONTRIBUTING.md, ROADMAP.md, and SECURITY.md kept at the root.

Keep The Boundary Clear

  • Keep human documentation useful without requiring private workspace context.
  • Put operational instructions for OpenClaw runtime agents in SKILL.md.
  • Put repository-maintenance guidance for coding agents in this file.
  • Do not add private paths, chat ids, cron ids, tokens, webhook URLs, personal notes, or generated research artifacts to public examples.
  • Do not mix hidden prompts or agent-only instructions into human-facing docs.

Before Changing Behavior

  • Read SKILL.md and the relevant helper modules under scripts/.
  • Preserve the cron-based execution model: Research Mode is an OpenClaw skill, not a standalone daemon or generic Python package.
  • Keep task state and artifacts task-local and path-contained.
  • Keep awaiting_review separate from delivered/completed state.
  • Keep finalization evidence explicit before a worker marks a result reviewable.

Verification

Run the release gate from the repository root after meaningful changes:

scripts/check_research_mode.sh

For documentation-only changes, at minimum run:

python3 scripts/check_research_mode_docs.py

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