agentleFS
Sign inStart free
adhyayanrathi01adhyayanrathi01/product-manager-os/skills/setup/AGENTS.md

product-manager-os / setup

AGENTS.md2 starsChanged 2 months agoMITView on GitHub

  • Reads credentials

The file

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

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Keep configuration provider-neutral and incremental.

    line 3
  2. Distinctive:

    Run only bounded read-only smoke tests, and only when the user and system permissions allow them.

    line 6
  3. Distinctive:

    Do not invent business definitions, permissions, identity mappings, metric rules, or source authority.

    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

Workspace-setup rules

  • Keep configuration provider-neutral and incremental; configure only what the user's intended workflows require.
  • Distinguish connected, authenticated, authorized, scoped, user-reported verification, agent-observed verification, and currently runtime-addressable access for every relevant source.
  • Record a non-secret invocation handle or a readable supplied-artifact path. Do not mark a source executable-ready from a user-reported prior test alone.
  • Run only bounded read-only smoke tests, and only when the user and system permissions allow them.
  • Store source pointers, scopes, definitions, limitations, verification times, environment-variable names, and secret-manager references; never store secret values.
  • Require an explicit stable cohort identity and merge/split treatment before declaring longitudinal account or workspace analysis ready.
  • With user permission, add only missing blank QA-variable declarations to a git-ignored, untracked local .env; never inspect, overwrite, or print secret values. Otherwise print only the exact variable names required and keep QA partial.
  • Preserve absolute authorization windows and last agent-observed verification dates in index.md summaries.
  • Do not invent business definitions, permissions, identity mappings, metric rules, or source authority.
  • Report every discovered skill as ready, partial, or blocked, with the exact evidence and smallest next action.

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