agentleFS
Sign inStart free
gabe4codinggabe4coding/retroagent/AGENTS.md

retroagent

AGENTS.md1 starsChanged 32 days agoMITView on GitHub

The code of retroagent: it syncs Claude Code and Codex sessions into a private data repo the user chooses, searches them with the kb CLI, and runs the cloud routine that writes project pages and weekly retros. This repo holds no data; each user's data lives in their own data repo.

  • 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 31,542 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 repository6 other files it gives its agents.

The file

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

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

  • 3

    Very specific

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

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

    Run a change end to end (/verify) → .claude/skills/verify/SKILL.md.

    line 11
  2. Very specific:

    Never write to a data clone by hand (root in the config).

    line 23
  3. Very specific:

    Only the machine that owns a host writes its folders in a data repo (own_paths in src/kb/sync.py), summaries included.

    line 24

≈ “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

retroagent

The code of retroagent: it syncs Claude Code and Codex sessions into a private data repo the user chooses, searches them with the kb CLI, and runs the cloud routine that writes project pages and weekly retros. This repo holds no data; each user's data lives in their own data repo.

Read first, by task

  • Code, tests, skills or docs → CODING_STANDARDS.md. User docs: README.md (pitch, quick start) and docs/*.mdx. The whole repo is the Claude Code / Codex plugin (marketplace source ./); bin/kb runs python3 -m kb from src/kb/.
  • Run a change end to end (/verify) → .claude/skills/verify/SKILL.md.
  • Install or setup → skills/setup/SKILL.md and install.sh.
  • The cloud routine → scripts/pages-routine.md.
  • Cloud sessions: the push from a cloud container and the import by one machine's sync → src/kb/cloud.py.
  • The data repo: layout and rules, what kb setup init / kb setup routine push (with {{CODE_REPO}} filled in) → templates/data/, AGENTS.md there first. How much each sync commit grows a data clone → scripts/raw-growth (read-only).

Rules

  • Develop in a checkout of its own. The installed copy (code in ~/.config/retroagent/config.json, usually ~/.retroagent) is what every kb on the machine runs; change it only with kb update. To try new code first, run this checkout's bin/kb (it runs the code next to it); keep to read-only commands such as find, show, sql.
  • Never write to a data clone by hand (root in the config). Use kb to read it: kb find, kb summary, kb show.
  • Only the machine that owns a host writes its folders in a data repo (own_paths in src/kb/sync.py), summaries included. Never write summaries from another machine or a cloud session, never with --force-host unless the owner asks, and never with a script that calls summarize, update_front_matter or write_catalog directly: the owner's next sync then conflicts.

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