Claude Code and Agent Conventions

anthropic

For some reason I believed Claude Code at least supported the AGENTS.md convention. It seems it neither supports that, nor the .agents folder convention.

First, I tried setting up a skill.

Terminal window
❯ tree .agents
.agents
└── skills
    └── chainlink
        ├── commands.md
        ├── hooks.md
        └── SKILL.md


3 directories, 3 files

Then ran claude:

❯ list the skills you see


⏺ Here are the available skills:


  1. update-config — Configure Claude Code settings
  (hooks, permissions, env vars, settings.json)
  1. keybindings-help — Customize keyboard shortcuts and
  keybindings
  1. verify — Run the app and observe behavior to verify
  a code change works
  1. code-review — Review the current diff for
  correctness bugs at a given effort level
  1. fewer-permission-prompts — Scan transcripts and add
  allowlists to reduce permission prompts
  1. loop — Run a prompt or slash command on a recurring
  interval
  1. claude-api — Build, debug, and optimize Claude API /
   Anthropic SDK apps
  2. run — Launch and drive the project's app to see a
  change working
  1. init — Initialize a new CLAUDE.md file with codebase
   documentation
  2.  review — Review a pull request
  3.  security-review — Complete a security review of
  pending changes on the current branch


  You can invoke any of these by typing /<skill-name>.


✻ Sautéed for 5s

This doesn’t work by default. The skill in the .agents folder isn’t automatically loaded by the Claude Code harness.

This same prompt indicates things do work when you switch to the .claude folder convention.

Terminal window
❯ tree .claude
.claude
└── skills
    └── chainlink
        ├── commands.md
        ├── hooks.md
        └── SKILL.md


3 directories, 3 files
❯ list the skills you see


⏺ Here are the available skills:


  1. chainlink — Track issues, sessions, and breadcrumbs
  with the chainlink CLI
  2. update-config — Configure Claude Code harness via
  settings.json (hooks, permissions, env vars)
  3. keybindings-help — Customize keyboard shortcuts and
  keybindings
  4. verify — Verify a code change works by running the
  app and observing behavior
  5. code-review — Review the current diff for
  correctness bugs
  6. fewer-permission-prompts — Scan transcripts and add
  allowlists to reduce permission prompts
  7. loop — Run a prompt or slash command on a recurring
  interval
  8. claude-api — Build, debug, and optimize Claude API /
   Anthropic SDK apps
  9. run — Launch and drive the project's app to see a
  change working
  10. init — Initialize a new CLAUDE.md file with
  codebase documentation
  11. review — Review a pull request
  12. security-review — Complete a security review of
  pending changes on the current branch


✻ Cogitated for 5s

The same lack of standard support can be seen with the agent markdown files.

AGENTS.md
My name is Bob
Terminal window
❯ what is my name


⏺ Based on your git config and email, your name is Dan
  Corin.
CLAUDE.md
My name is Bob
Terminal window
❯ what is my name


⏺ Your name is Bob.

Codex

Per my testing today, Codex seems to now support both provider-agnostic conventions AGENTS.md and a .agents folder.

raw edit commit

Recommended

Claude Code Custom Slash Commands Hierarchy

Claude Code supports custom slash commands. Custom slash commands allow you to define frequently-used prompts as Markdown files that Claude Code can...

Reviving a Raspberry Pi with Claude Code

Sometime in 2021 (I think), I got a Raspberry Pi 4 and played with it a little and then it started collecting dust on my desk. Every time I looked at...

Claude Code

Today, Anthropic entered the LLM code tools party with Claude Code.