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/muhammedzohaib/patchman/claude-mdgit clone --depth 1 https://github.com/MuhammedZohaib/patchmanWhat 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 | $0.00118 | $0.00118 |
| Opus 5 | $0.00059 | $0.00059 |
| Sonnet 5 | $0.00024 | $0.00024 |
| Haiku 4.5 | $0.00012 | $0.00012 |
Grade A, and why
patchman 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 2d 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.
What it actually says
CLAUDE.md
When Patchman is active:
- behave like a defensive appsec reviewer, not an operator
- use review-first language and evidence-based findings
- prefer code references over generic advice
- explain exploitability safely and without payload chains
- suggest contained remediations and follow-up checks
Standard finding sections:
- Title
- Severity
- Confidence
- CWE / OWASP mapping
- Affected area
- Why this matters
- Evidence
- Exploitability notes
- Recommended fix
- Safer example patch
- Follow-up checks
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.
- 2d ago First seen · 24 lines · 118 tokens per session scan A 3874ecd156b2
patchman CLAUDE.md is an instructions file published in the GitHub repository MuhammedZohaib/patchman (3 stars, last pushed 4mo ago), licensed MIT. It adds 118 tokens to every session, about $0.0006 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 2026-08-31.
Other instructions, from other repositories
thunderid AGENTS.md
Instructions for thunder-id/thunderid, covering project overview, where to look next, search hygiene, validation ladder and product name rules.
thunderid copilot-instructions.md
Instructions for thunder-id/thunderid: All project coding standards, conventions, and guidelines are defined in AGENTS.md.
golf CLAUDE.md
Instructions for golf-mcp/golf, covering claude.md, project overview, breaking changes in golf 0.2.x, key architecture and common development commands.
gvray-admin CLAUDE.md
Instructions for gvray/gvray-admin, covering gvray admin — claude code 指南, 项目概况, 关键目录, 开发硬规则 and 按需阅读.
server copilot-instructions.md
Instructions for mcpambassador/server, covering mcp ambassador server — copilot instructions, repo context, monorepo package structure, architecture patterns and spi (service provider interface).
server AGENTS.md
Instructions for mcpambassador/server, covering project instructions, current state, working agreements, definition of done — ci gate (mandatory) and common gotchas.