patchman CLAUDE.md

Project instructions for a defensive application-security review skill. It examines code and web apps for common security weaknesses, including access-control errors, leaked secrets, and unsafe data handling.

In plain words
What is it for?
Use it to review an application for OWASP Top 10 risks, authentication and authorization problems, tenant-isolation issues, business-logic bugs, and database query problems.
Why use it?
It gives security findings a consistent format and keeps the review focused on evidence, safe explanations, and contained fixes.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/muhammedzohaib/patchman/claude-md
Clone the repo
git clone --depth 1 https://github.com/MuhammedZohaib/patchman
Per session 118 This file is loaded in full into every session.
When invoked 118 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found 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 $0.00118 $0.00118
Opus 5 $0.00059 $0.00059
Sonnet 5 $0.00024 $0.00024
Haiku 4.5 $0.00012 $0.00012

Measured 2d ago against content hash 3874ecd156b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

CLAUDE.md · 24 lines

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
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. 2d ago First seen · 24 lines · 118 tokens per session scan A 3874ecd156b2

Subscribe to this mod's changes

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.