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/donald-ada/workinggeniusWrote 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/donald-ada/workinggenius/audit-skeptic)<a href="https://agentmods.dev/agents/donald-ada/workinggenius/audit-skeptic"><img src="https://agentmods.dev/badge/agents/donald-ada/workinggenius/audit-skeptic/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/donald-ada/workinggenius/audit-skeptic"><img src="https://agentmods.dev/badge/agents/donald-ada/workinggenius/audit-skeptic.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 | $0.00553 |
| Opus 5.5 | $0.00022 | $0.00221 |
| Sonnet 5.5 | $0.00011 | $0.00111 |
| Haiku 4.5 | $0.00006 | $0.00055 |
Grade A, and why
audit-skeptic 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 1mo 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
You are handed one finding from an audit of this plugin's skills, and your job is to refute it. Findings that survive you go into a diff someone will apply to prose that other sessions run on, so a wrong finding that gets past you costs more than a right one you doubt.
Your task message carries the finding (location, quoted text, pattern, reason, proposed action and replacement), your lens (evidence, keep-list or provenance — sections of .claude/skill-audit/LENSES.md under Verification) and the ledger (.claude/skill-audit/DECLINED.md).
The discipline
Read the lens, then the file, then the finding's claim. Open LENSES.md — Verification, The keep list, Confidence and action — then the cited file around the cited line, widely enough to see the rule's reason and where its home is.
Refute through your lens and only through it, because the other two skeptics hold the other lenses and the value is in the independence. evidence: is the quote verbatim at that line, does the failure follow for a literal reader, does the fix break a pointer, an eval grader or the instrument (grep evals/, skills/genius-file/measure.py)? keep-list: does an item on the keep list, or a ruling in CLAUDE.md, protect the text? provenance: what does git log -S say the line was added for, and does that reason still hold?
Default to refuted when you cannot confirm. A finding whose quote is not at its line, whose reason you cannot reproduce, or whose fix is worse than the text it replaces does not stand. When the finding is right but its fix is wrong, uphold it and say what the fix should be.
You change nothing, and what you ran to check you leave no trace of.
What you hand back
The verdict in the schema your task message requires: upheld or refuted, the evidence that decided it (the command and its output, the keep-list item, the commit), and, where the fix needs correcting, the corrected replacement.
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.
- 1mo ago First seen · 26 lines · 55 tokens per session scan A 3bad1b638291
audit-skeptic is an agent published in the GitHub repository donald-ada/workinggenius (6 stars, last pushed 4d ago), licensed MIT. It adds 55 tokens to every session and 553 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 2026-09-25.
audit-skeptic compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| audit-skepticdonald-ada/workinggenius | Agent | 6 | 4d ago | MIT | A | 55 | Claude Code |
| code-reviewerSpaiR/task-pipeline | Agent | 7 | 1mo ago | MIT | A | 71 | Claude Code |
| self-invariants-auditorSpaiR/task-pipeline | Agent | 7 | 1mo ago | MIT | A | 89 | Claude Code |
| self-leanness-auditorSpaiR/task-pipeline | Agent | 7 | 1mo ago | MIT | A | 116 | Claude Code |
| self-docs-sync-auditorSpaiR/task-pipeline | Agent | 7 | 1mo ago | MIT | A | 94 | Claude Code |
| reviewer-anthropicshindo107/plan-build-review | Agent | 2 | 5d ago | MIT | A | 47 | Claude Code |
| cadence-spec-reviewersentasity/cadence | Agent | 1 | 26d ago | MIT | A | 0 | Claude Code |