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 commands/muhammedzohaib/patchman/audit-reportgit 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 | $0.00000 | $0.00056 |
| Opus 5 | $0.00000 | $0.00028 |
| Sonnet 5 | $0.00000 | $0.00011 |
| Haiku 4.5 | $0.00000 | $0.00006 |
Grade A, and why
audit-report 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
/audit-report
Converts raw findings into an engineering-ready report.
Prompt template
Turn the current findings into an audit report with executive summary, methodology, prioritized findings, remediation plan, and assumptions / unknowns. Keep it concise and technical.
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 · 10 lines · 0 tokens per session scan A 0b1d537e1b01
audit-report is a command published in the GitHub repository MuhammedZohaib/patchman (3 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 56 tokens. 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 commands, from other repositories
sicario.verify
Run deterministic verification.
sinks
Search the codebase for dangerous functions that could lead to vulnerabilities. Optionally auto-discover logging patterns and sensitive data sources.
token-scan
Command "token-scan" from Zyrexnn/Cybermes, covering /token-scan, usage, step 0: quick kill signals, step 1: optional automated scanner and if present.
triage
Command "triage" from Zyrexnn/Cybermes, covering /triage, when to use, usage, the 7 questions (fast version) and fast kill checklist.
intel
Command "intel" from Zyrexnn/Cybermes, covering /intel, what this does, usage, output and data sources.
surface
Command "surface" from Zyrexnn/Cybermes, covering /surface, what this does, usage, prerequisites and output.