agentleFS
Sign inStart free
wyattjohwyattjoh/skills/.claude/rules/agents.md

skills / rules

AGENTS.md3 starsChanged 46 days agoMITView on GitHub

Agent authoring conventions including frontmatter fields, reload behavior, and validation

The file

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

2 rules. About 0 are common, 0 are distinctive, and 2 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.

  • 2

    Very specific

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

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

    Use the plugin-dev:plugin-validator agent to validate agent definitions before merging.

    line 30
  2. Very specific:

    When adding or removing an agent, update the agents table in README.md so the documented agent list stays in sync with the actual contents …

    line 34

≈ “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

Agent definitions live at agents/<name>.md as markdown files with YAML frontmatter.

Frontmatter fields

  • name: kebab-case identifier
  • description: Delegation trigger: what the agent does and the situations that should route to it. Add urgency such as "Use PROACTIVELY" only for an agent that demonstrably under-delegates, scoped to that situation.
  • tools: Allowed tools. Two accepted forms:
    • Comma-separated scalar string: tools: "Bash, Read, Grep"
    • YAML list (required when entries contain colons or spaces): tools:\n - Read\n - "Bash(jq:*)" Omit the field to inherit all tools from the parent session.
  • model: inherit, haiku, sonnet, or opus
  • skills: Skills to autoload (subagents don't inherit parent skills)
  • permissionMode: default, acceptEdits, bypassPermissions, plan
  • memory: Persistence scope. user stores memory per-user across sessions. Version-sensitive: verify against the installed Claude Code release.
  • color: Label color shown in the Claude Code UI (e.g. cyan). Version-sensitive: verify against the installed Claude Code release.

Reload behavior

Agents require a Claude Code restart to pick up changes. Skills, by contrast, hot-reload.

Validation

Use the plugin-dev:plugin-validator agent to validate agent definitions before merging.

Documentation sync

When adding or removing an agent, update the agents table in README.md so the documented agent list stays in sync with the actual contents of agents/.

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