agentleFS
Sign inStart free
lthoangglthoangg/OpenAgentd/.agents/AGENTS.md

OpenAgentd

AGENTS.md217 starsChanged 28 days agoApache-2.0View on GitHub

This subtree contains tracked commands, snippets, and skills used while working on OpenAgentd. It does not contain the application's user-owned runtime configuration. - commands/*.md: slash commands ($ARGUMENTS is the user's argument). - snippets/**/*.md: one-line shell snippets. - skills/oad/<name>/SKILL.md: repository workflows — commit, debug (including logs and telemetry), release, review, testing (including test-first). skills/guidelines/ holds general coding behavior. - plans/: OpenAgentd session plans; ignored through its own .gitignore. - Command and snippet Markdown files require YAML frontmatter with a description field.…

  • Reads credentials
  • 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 31,700 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 repository8 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:

    Every skill entry point is a SKILL.md with name (matching its path, e.g.

    line 20
  2. Very specific:

    Keep commands non-destructive by default.

    line 26
  3. Very specific:

    Do not edit ignored .agents/plans/, the local .openagentd/ runtime tree (dev/, sessions/, state/, …), or other runtime output as repository …

    line 28

≈ “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

Repository Agent Assets

This subtree contains tracked commands, snippets, and skills used while working on OpenAgentd. It does not contain the application's user-owned runtime configuration.

Layout

  • commands/*.md: slash commands ($ARGUMENTS is the user's argument).
  • snippets/**/*.md: one-line shell snippets.
  • skills/oad/<name>/SKILL.md: repository workflows — commit, debug (including logs and telemetry), release, review, testing (including test-first). skills/guidelines/ holds general coding behavior.
  • plans/: OpenAgentd session plans; ignored through its own .gitignore.

File contracts

  • Command and snippet Markdown files require YAML frontmatter with a description field.
  • Every skill entry point is a SKILL.md with name (matching its path, e.g. oad/testing) and description frontmatter. Keep detailed supporting material in that skill's references/ or scripts/ directory (Agent Skills spec folder names), and keep commands and paths in skills true to the Makefiles and scripts they name.
  • Commands delegate to skills rather than restating them.
  • Keep commands non-destructive by default. Never embed credentials, machine-local paths, or copied .env values.
  • Do not edit ignored .agents/plans/, the local .openagentd/ runtime tree (dev/, sessions/, state/, …), or other runtime output as repository source.

Checks

make verify-docs

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