Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/rlajous/claude-code-commands/claude-mdgit clone --depth 1 https://github.com/rlajous/claude-code-commandsWrote 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.
[](https://agentmods.dev/instructions/rlajous/claude-code-commands/claude-md)<a href="https://agentmods.dev/instructions/rlajous/claude-code-commands/claude-md"><img src="https://agentmods.dev/badge/instructions/rlajous/claude-code-commands/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.02365 | $0.02365 |
| Opus 5 | $0.01182 | $0.01182 |
| Sonnet 5 | $0.00473 | $0.00473 |
| Haiku 4.5 | $0.00236 | $0.00236 |
Grade A, and why
claude-code-commands CLAUDE.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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Overview
This repository is the dual-runtime Git Workflow package. Claude Code consumes its marketplace/plugin packaging and Claude-specific frontmatter; Codex consumes .codex-plugin/plugin.json and generated .codex/agents/*.toml. Shared workflow configuration lives in .git-workflow/config.yaml, with legacy .claude/config.yaml reads retained for compatibility.
Behavioral Guidelines
- Strictly Reactive: Only perform the specific task requested. Do not perform follow-up research, planning for future phases, or speculative actions unless explicitly asked.
- Seek Confirmation: Always wait for user confirmation after completing a discrete task before moving to anything else.
- No Unapproved Side Effects: Do not apply database migrations, execute scripts, or modify the system state without explicit approval for that specific action.
Repository Structure
.claude-plugin/
├── marketplace.json # Marketplace catalog for distribution
└── plugin.json # Plugin manifest
.codex-plugin/
└── plugin.json # Codex plugin manifest
.codex/agents/ # Generated Codex project agents (do not hand-edit)
skills/ # Skills (each an invocable slash command via SKILL.md)
├── setup/SKILL.md # Interactive setup wizard
├── start/SKILL.md # Create feature branch from ticket
├── plan-tdd/SKILL.md # Design a reviewed TDD plan before coding
├── tdd/SKILL.md # Test-Driven Development workflow
├── commit/SKILL.md # Stage and commit with conventions
├── finish/SKILL.md # Create PR with full description
├── review/SKILL.md # Comprehensive code review on a PR
├── release/SKILL.md # Create release branch and PR
├── release-notes/SKILL.md # Generate GitHub release notes
├── sync/SKILL.md # Back-merge main to development
├── plan-qa/SKILL.md # Generate QA test plan
├── start-qa/SKILL.md # Execute QA tests
├── rfc/SKILL.md # Create an auto-numbered RFC document
├── review-request/SKILL.md # Draft a paste-ready PR review request
├── standup/SKILL.md # Async standup from recent activity
├── update/SKILL.md # Update skills/agents from source
├── clean-gone/SKILL.md # Delete local branches gone on the remote
├── status/SKILL.md # Show workflow position and next step
├── review-watch/SKILL.md # Auto-review PRs that request your review, in a loop
├── notifications/SKILL.md # Opt-in agent and authored-PR activity alerts
└── change-brief/SKILL.md # Self-contained HTML explainer of a change
agents/ # Subagents for specialized tasks
├── pr-reviewer.md # Code review agent
├── release-validator.md # Release validation agent
└── qa-executor.md # QA test execution agent
templates/
├── config.yaml.template # Configuration template
├── settings.json.template # Hooks configuration template
└── CLAUDE.md.template # CLAUDE.md template for projects
examples/ # Stack-specific examples
├── nestjs/ # NestJS backend config
├── nextjs/ # Next.js frontend config
├── python/ # Python FastAPI config
├── react-native/ # React Native config
└── monorepo/ # Turborepo monorepo config
README.md # Main documentation
INSTALLATION.md # Setup guide
CONFIGURATION.md # Configuration reference
COMMANDS.md # Commands reference documentation
AGENTS.md # Concise Codex contributor guidance
docs/SUBAGENTS.md # User-facing agent catalog
HOOKS.md # Hooks documentation
LICENSE # MIT license
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.
- 4d ago First seen · 233 lines · 2,365 tokens per session scan A e24cd180c543
claude-code-commands CLAUDE.md is an instructions file published in the GitHub repository rlajous/claude-code-commands (30 stars, last pushed 5d ago), licensed MIT. It adds 2,365 tokens to every session, about $0.0118 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.