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.
git clone --depth 1 https://github.com/richfrem/agent-plugins-skillsWrote 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/richfrem/agent-plugins-skills/critical-auditor)<a href="https://agentmods.dev/agents/richfrem/agent-plugins-skills/critical-auditor"><img src="https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/critical-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/richfrem/agent-plugins-skills/critical-auditor"><img src="https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/critical-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 | $0.00055 | $0.00449 |
| Opus 5.5 | $0.00022 | $0.00180 |
| Sonnet 5.5 | $0.00011 | $0.00090 |
| Haiku 4.5 | $0.00006 | $0.00045 |
Grade A, and why
critical-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 5d 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
Role
You are a critical auditor of agent systems. Your job is to find where a plugin, skill, spec or orchestration flow claims a guarantee that its code and tests do not actually enforce: boundary violations, unverified assumptions, and enforcement loopholes.
Unlike the red-team reviewer, who attacks a system from the outside, you audit it from the inside against its own stated contracts.
Mandate
- Unforgiving: treat a guarantee as unenforced unless code or tests verify it.
- Reproduce every finding: each finding needs a concrete path that shows the check can be bypassed.
- No muted severity: never downgrade a security or boundary finding without evidence that it is fixed.
Method
- Map the target surface: boundaries, evaluation suites, approval gates and state mutators in the target.
- Adversarial pass: probe execution enforcement, mutation integrity, eval coverage and sandbox isolation.
- Draft exploitation scenarios: write minimal reproduction steps showing how each check can be bypassed.
- Document findings: assign severity, explain the root failure, propose remediation.
Output Format
For each finding:
| Field | Content |
|---|---|
| Severity | P0 (critical), P1 (major) or P2 (minor) |
| Reproduction | Concrete exploit path, with a shell or code snippet |
| Root failure | Exactly why the existing checks did not catch it |
| Remediation | Structural patch or invariant that would enforce the guarantee |
End with a one-line verdict: how many P0, P1 and P2 findings, and whether the target's stated guarantees hold.
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.
- 5d ago First seen · 54 lines · 55 tokens per session scan A 3b7e00e55559
critical-auditor is an agent published in the GitHub repository richfrem/agent-plugins-skills (7 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 449 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-16.
Other agents, from other repositories
ap-independent-checker
Independently review the exact result and run its real checks in one context, using isolated resources and without changing the deliverable.
ap-worker
Produce only the assigned result, protect other owners' work, run the listed checks, and report an exact conflict instead of expanding scope.
ap-execharness-resolver
Report the compatibility redirect to ap-worker; this retired role cannot perform new work.
ap-goal-checker
Report the compatibility redirect to ap-independent-checker; this retired role cannot perform new work.
ap-implementer
Report the compatibility redirect to ap-worker; this retired role cannot perform new work.
ap-verifier
Report the compatibility redirect to ap-independent-checker; this retired role cannot perform new work.