claude-plugins: Instructions file for Codex

AGENTS.md

claude-plugins AGENTS.md is an instructions file for Codex, OpenCode from gm2211/claude-plugins. It costs 488 tokens per session, scanned A, a copy of awesome-spain AGENTS.md, MIT.

Project instructions for AGENTS.md in a repository that uses Beads, an issue-tracking tool, and Git worktrees, separate working copies of a repository.

In plain words
What is it for?
Following the repository’s issue workflow, quality checks, session handoff steps, and required Git push process.
Why use it?
They define the required process for claiming and closing issues, checking changes, synchronising work, and pushing completed code.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions .claude-plugin.

This is gm2211/claude-plugins's own configuration. It tells Codex and OpenCode how to work on claude-plugins itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-plugins configures →

Reuse

Borrowing it

Nothing to install: this file belongs to gm2211/claude-plugins. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/gm2211/claude-plugins/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/gm2211/claude-plugins

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for claude-plugins AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/gm2211/claude-plugins/agents-md/github.svg)](https://agentmods.dev/instructions/gm2211/claude-plugins/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/gm2211/claude-plugins/agents-md"><img src="https://agentmods.dev/badge/instructions/gm2211/claude-plugins/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for claude-plugins AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/gm2211/claude-plugins/agents-md"><img src="https://agentmods.dev/badge/instructions/gm2211/claude-plugins/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 488 This file is loaded in full into every session.
When invoked 488 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 63% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00488 $0.00488
Opus 5.5 $0.00195 $0.00195
Sonnet 5.5 $0.00098 $0.00098
Haiku 4.5 $0.00049 $0.00049

Measured 3d ago against content hash fe1f8c09ed75, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claude-plugins AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

63% identical to awesome-spain AGENTS.md — 118 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

AGENTS.md · 50 lines

What it actually says

Agent Instructions

Issue tracking

Tasks are GitHub Issues, managed with the gh CLI:

gh issue list                                       # Find open work
gh issue create --title "..." --body "..."          # File a task
gh issue close <n> --comment "Completed in #<pr>"   # Complete work

For follow-up work discovered along the way, file a new issue and reference the parent issue number (for example "Follow-up to #12") in the body.

Landing the Plane (Session Completion)

When ending a work session, you MUST complete ALL steps below. Work is NOT complete until git push succeeds.

MANDATORY WORKFLOW:

  1. File issues for remaining work - Create GitHub Issues for anything that needs follow-up
  2. Run quality gates (if code changed) - Tests, linters, builds
  3. Update issue status - Close finished issues, comment on in-progress ones
  4. PUSH TO REMOTE - This is MANDATORY:
    git pull --rebase
    git push
    git status  # MUST show "up to date with origin"
    
  5. Clean up - Clear stashes, prune remote branches
  6. Verify - All changes committed AND pushed
  7. Hand off - Provide context for next session

CRITICAL RULES:

  • Work is NOT complete until git push succeeds
  • NEVER stop before pushing - that leaves work stranded locally
  • NEVER say "ready to push when you are" - YOU must push
  • If push fails, resolve and retry until it succeeds

Repo-specific: if you add plugins back to this repo, bump the version in .claude-plugin/marketplace.json on every commit that changes plugin files.

Worktree Convention

When the coordinator dispatches you with REPO_ROOT and EPIC_BRANCH:

  1. cd $REPO_ROOT
  2. git worktree add .worktrees/${EPIC_BRANCH}--<your-task-slug> -b ${EPIC_BRANCH}--<your-task-slug>
  3. cd .worktrees/${EPIC_BRANCH}--<your-task-slug>
  4. Do all work in this worktree
  5. Commit and push your branch when done
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago Changed · -29 lines · -260 tokens per session fe1f8c09ed75
  2. 1mo ago Changed · -18 lines · -134 tokens per session 1f270805658a
  3. 2mo ago First seen · 97 lines · 882 tokens per session scan A 8ea71f453e99

Subscribe to this mod's changes

claude-plugins AGENTS.md is an instructions file published in the GitHub repository gm2211/claude-plugins (2 stars, last pushed 3d ago), licensed MIT. It adds 488 tokens to every session, about $0.0020 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 63% identical to awesome-spain AGENTS.md, differing in 118 lines, and is treated as a copy.

Related

claude-plugins AGENTS.md compared with instructions from other repositories

claude-plugins AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
claude-plugins AGENTS.mdgm2211/claude-pluginsInstructions file23d agoMITA488Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode