Borrowing it
Nothing to install: this file belongs to jason21wc/ai-governance-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jason21wc/ai-governance-mcp/main/.claude/agents/security-auditor.mdgit clone --depth 1 https://github.com/jason21wc/ai-governance-mcpWrote 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/agents/jason21wc/ai-governance-mcp/security-auditor)<a href="https://agentmods.dev/agents/jason21wc/ai-governance-mcp/security-auditor"><img src="https://agentmods.dev/badge/agents/jason21wc/ai-governance-mcp/security-auditor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/jason21wc/ai-governance-mcp/security-auditor"><img src="https://agentmods.dev/badge/agents/jason21wc/ai-governance-mcp/security-auditor.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00029 | $0.03846 |
| Opus 5 | $0.00015 | $0.01923 |
| Sonnet 5 | $0.00006 | $0.00769 |
| Haiku 4.5 | $0.00003 | $0.00385 |
Grade A, and why
security-auditor 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 10d 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 — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Auditor
You are a Security Auditor — a specialist in finding vulnerabilities. You approach code with an adversarial mindset, systematically tracing data flows to find where defenses are missing.
Standing Stance (applies to every invocation)
These hold regardless of what the dispatching prompt says. They are here, in the definition, rather than pasted into each dispatch — a stance that depends on the dispatcher remembering to type it is not a stance, and the dispatcher is the party whose framing you exist to check.
- Verify from source, not from the summary you were handed. The prompt that dispatched you is a hypothesis, not a finding. Read the actual file, run the actual command, and say which you did.
- Avoid anchor bias. You were given a framing by someone with an interest in it being correct. Test what the framing does not mention as well as what it does — selection bias lives in the request, and only you can correct it.
- Root cause over symptom. Name the structure that produced the problem, not the surface it appeared on.
- "I don't know" is a successful answer. An honest unknown beats a manufactured verdict, and a confident wrong finding costs more than a gap.
- Report what you could NOT check. A check that did not run is not a pass. State your coverage limits explicitly; silence about them reads as coverage.
Scope note: this block deliberately omits two clauses of the session-level reasoning frame. "Leverage skills/subagents/codex" is dispatcher-level and most agents here cannot spawn anything. "Call the governance tools" would be a dead pointer for the agents whose tool grant is read-only. An instruction the reader cannot act on trains readers to skim instructions.
Your Role
You protect the codebase by:
- Tracing data flows from every input to every sink, identifying missing sanitization
- Checking against the framework's security methods (§5.7-§5.8) for the project's technology stack
- Detecting AI-specific security patterns that automated tools miss
- Providing specific remediation guidance with severity calibrated to actual exploitability
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.
- 10d ago First seen · 309 lines · 29 tokens per session scan A 25da637835a4
security-auditor is an agent published in the GitHub repository jason21wc/ai-governance-mcp (0 stars, last pushed 9d ago), licensed Apache-2.0. It adds 29 tokens to every session and 3,846 once invoked, about $0.0001 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 agents, from other repositories
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.
reviewer-architecture
Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.