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/leanandmean/mach10/claude-mdgit clone --depth 1 https://github.com/LeanAndMean/mach10Wrote 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/leanandmean/mach10/claude-md)<a href="https://agentmods.dev/instructions/leanandmean/mach10/claude-md"><img src="https://agentmods.dev/badge/instructions/leanandmean/mach10/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 | $0.05751 | $0.05751 |
| Opus 5 | $0.02875 | $0.02875 |
| Sonnet 5 | $0.01150 | $0.01150 |
| Haiku 4.5 | $0.00575 | $0.00575 |
Grade A, and why
mach10 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 — 151 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.
Project Overview
mach10 defines a structured development methodology for agentic coding and provides a Claude Code plugin that implements it. The methodology centers on fresh sessions for each step, GitHub as the inter-session persistence layer, staged implementation, and iterative review-fix cycles. The plugin codifies this into 14 slash commands covering the complete issue-to-merge lifecycle.
Architecture
This is a pure plugin definition -- no build system, no runtime, no tests. Claude Code reads the command files directly.
.claude-plugin/plugin.json # Plugin manifest (name, version, author)
agents/ # Specialized agent definitions (markdown with YAML frontmatter)
commands/ # Slash command definitions (markdown with YAML frontmatter)
scripts/ # Utility scripts (repo maintenance, data collection)
Each command file is a self-contained workflow specification with:
- YAML frontmatter:
description,argument-hint,allowed-tools - Markdown body: Step-by-step instructions Claude Code follows when the command is invoked
Command Structure
Issue workflow: issue-assessment, issue-plan, issue-plan-review, issue-implement, issue-create
PR workflow: pr-create, pr-review, pr-review-fix, pr-ci-fix, doc-review, pr-pre-merge, pr-merge
Utilities: push, test-audit
Key Design Decisions
- Thin orchestration: Commands gather context and delegate to
feature-devandpr-review-toolkitplugins via the Skill tool rather than reimplementing workflows. - Single-concern sessions: Review and fix are separate commands to preserve context budget for implementation. Each command is designed to run in a fresh CLI session.
- GitHub as backbone: Plans, reviews, and progress are posted as issue/PR comments so context persists across sessions.
- Safe defaults: No
git add -A, no staging of secrets, no force-pushes, branch deletion uses-dflag.
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 · 151 lines · 5,751 tokens per session scan A cae4b640cb5e
mach10 CLAUDE.md is an instructions file published in the GitHub repository LeanAndMean/mach10 (20 stars, last pushed 3mo ago), licensed MIT. It adds 5,751 tokens to every session, about $0.0288 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
catalyst AGENTS.md
AGENTS.md instructions for coalesce-labs/catalyst, covering agents.md, what this repository is, agent philosophy, build & test and key principles.
claude-sdlc CLAUDE.md
Claude Code instructions for lantisprime/claude-sdlc, covering claude.md, what this repo is, design intent — read this before "improving" anything, eat your own dog food and hook strictness philosophy.
auto-pilot CLAUDE.md
Claude Code instructions for IronRookieCoder/auto-pilot, covering 项目概况 and 同步更新规则.
Starlight-Intelligence-System AGENTS.md
AGENTS.md instructions for frankxai/Starlight-Intelligence-System, covering frank dna, standards, multi-agent systems & agent harnesses, 1. what makes sis unique and 2. the swarm harness process.
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.