agentleFS
bex-cobex-co/bex/.pm/AGENTS.md

bex

AGENTS.md576 starsChanged 15 days agoApache-2.0View on GitHub

Internal PM board — see README.md. /pm is the only skill that writes here; its conventions live in .claude/skills/pm/SKILL.md. The board is markdown and small text (user decision 2026-11-04, w6/100 D10). Never commit build artifacts or bulk evidence here: no file over 1 MiB and no whl/gz/tar/zip/bin/image/pdf/database file under .pm/. Raw run output of any size is evidence too: no *evidence* directory, no json/jsonl/log/stdout/stderr or *evidence*.txt file anywhere under .pm/ (second history rewrite, 2026-11-04). Keep it in a local evidence/…

The file

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

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When work is completed, do not leave it in place — move it:

    line 11

≈ “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

.pm/AGENTS.md

Internal PM board — see README.md. /pm is the only skill that writes here; its conventions live in .claude/skills/pm/SKILL.md.

Evidence lives outside git

The board is markdown and small text (user decision 2026-11-04, w6/100 D10). Never commit build artifacts or bulk evidence here: no file over 1 MiB and no whl/gz/tar/zip/bin/image/pdf/database file under .pm/. Raw run output of any size is evidence too: no *evidence* directory, no json/jsonl/log/stdout/stderr or *evidence*.txt file anywhere under .pm/ (second history rewrite, 2026-11-04). Keep it in a local evidence/ directory (gitignored) or upload it, and write the conclusion, the sha256 and the link into the item's markdown. scripts/repo-artifact-guard.sh rejects violations at ship time and in CI.

Done items move to done/ folders

When work is completed, do not leave it in place — move it:

  • Task done (wN/mN/tNNN.md): set frontmatter status: done, mark its row — **DONE** in the milestone README.md and update the **Status:** line, then move the file to wN/mN/done/tNNN.md.
  • Milestone done (no open tasks left in wN/mN/): move the whole milestone directory to wN/done/mN/ (mv the directory, then rmdir the empty original — never leave a tombstone, stub, or redirect README at the old path; a done milestone's original path must simply not exist) and check its box (- [x]) in the workstream README.md.
  • Inbox note done (wN/NNN.md): move it to wN/done/NNN.md (e.g. w1/done/001.md).

Keep status in sync across all three places it lives: the workstream README checkbox, the milestone README **Status:** line + task-table — DONE markers, and each task's status: frontmatter. When scanning the board for open work, skip done/ directories. If a /goal (or other tooling) references a milestone by its pre-move path, that path is expected to disappear on completion — do not recreate 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.