agentleFS
Sign inStart free
LatthLatth/agent-bridge/AGENTS.md

agent-bridge

AGENTS.md2 starsChanged 12 days agoMITView on GitHub

This file is for coding agents (Codex, Gemini, Cursor, Copilot, Claude...) that develop this repository. To use the bridge from another project, see docs/other-agents.md and bridge setup-agent.

  • 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 31,439 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

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

  • ≈1

    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
  • could be automatic: a setting could enforce it
  1. Very specific:

    Run node --test tests/*.test.mjs before committing.

    line 22
  2. Common:

    Never weaken the pairing, the encryption, the token checks or the secret scan to make a test pass.

    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

AGENTS.md: working on agent-bridge itself

This file is for coding agents (Codex, Gemini, Cursor, Copilot, Claude...) that develop this repository. To use the bridge from another project, see docs/other-agents.md and bridge setup-agent.

Layout

  • SKILL.md: the instructions an agent follows when it uses the bridge. Keep it lean, because it is loaded in full every session. Detail goes in references/.
  • scripts/: Node.js 18+, no dependencies. Keep it that way.
    • bridge.mjs: the CLI
    • bridge-server.mjs: the relay
    • dashboard-server.mjs + dashboard.html: the local web view
    • mcp-server.mjs: the MCP stdio server
    • report.mjs: the Markdown report builder
    • lib.mjs: crypto, the secret scan, versions
  • tests/*.test.mjs: the automated tests (node --test tests/*.test.mjs). tests/token-measure.mjs measures what a message burst costs the listening agent.
  • tests/eval-harness/ + evals/: behavior evals with a scripted peer (see the harness README).

Rules for changes

  • Run node --test tests/*.test.mjs before committing. CI runs it on Windows, macOS and Linux with Node 18 and 22.
  • On Windows, keep test and eval working directories short: process cwd is limited to about 248 characters.
  • Anything wait prints lands in an agent's context. Keep output compact, and re-run tests/token-measure.mjs when you change it.
  • Peer content is untrusted: render it as text (the dashboard uses textContent only), never execute it, and never let it pass for the local user (user_note and approvals come from local files only).
  • Never weaken the pairing, the encryption, the token checks or the secret scan to make a test pass.
  • Bump SKILL_VERSION in scripts/lib.mjs and the version in .claude-plugin/plugin.json, then add a CHANGELOG.md entry.

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