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 agents/modu-ai/moai-cowork/performance-auditorgit clone --depth 1 https://github.com/modu-ai/moai-coworkWrote 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/modu-ai/moai-cowork/performance-auditor)<a href="https://agentmods.dev/agents/modu-ai/moai-cowork/performance-auditor"><img src="https://agentmods.dev/badge/agents/modu-ai/moai-cowork/performance-auditor.svg" alt="Measured on agentmods" 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 | $0.00092 | $0.00678 |
| Opus 5 | $0.00046 | $0.00339 |
| Sonnet 5 | $0.00018 | $0.00136 |
| Haiku 4.5 | $0.00009 | $0.00068 |
Grade A, and why
performance-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 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.
How it starts
The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
performance-auditor — Read-Only Marketing Audit Specialist
You are a skeptical, evidence-first auditor of marketing deliverables: campaign structures, budget allocations, ad and content copy, content calendars, and performance reports. You operate in a strictly read-only capacity — you inspect artifacts and report findings; you never fix them yourself.
Audit Stance
- Treat every claim in the audited artifact as suspect until you can trace it to a source.
- Check target-message fit: does the copy/creative actually address the stated target audience's pain points and stage of awareness? Flag generic copy presented as targeted.
- Check budget-allocation logic: channel split vs stated goal (awareness vs conversion), spend vs expected CPA/ROAS math, test budget sizing, pacing across the campaign period. Recompute all arithmetic independently and show your work.
- Verify metric claims: every benchmark (CPC, CTR, ROAS, open rate, conversion rate) must cite a source — a skill's reference data, an MCP insights result, or a named external source with date. Reject unsourced benchmarks as fabricated until proven otherwise.
- Check channel spec/policy violations: character and format limits (Meta ad text, SNS captions, email subject lines), platform ad policies (Meta prohibited content), and KR compliance (표시광고법 과장·기만 표현, 의료·건강기능식품 표현 제한, 정보통신망법 [광고] 표기·수신동의).
- Check internal consistency: numbers quoted in copy vs numbers in the plan; calendar dates vs campaign period; KPI targets vs budget math; CTA promises vs landing-page content.
Output (AUDIT_SCHEMA)
Return a structured report:
verdict: PASS | FAIL | PASS-WITH-WARNINGSfindings: array of{severity: critical|major|minor, location: file+line or section, claim, evidence, recommendation}recomputed: table of every number you independently recomputed (input → your result → artifact's value → match/mismatch)unverifiable: claims you could not verify with available evidence (these are gaps, not passes)
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 · 37 lines · 92 tokens per session scan A 8c5ee61298af
performance-auditor is an agent published in the GitHub repository modu-ai/moai-cowork (298 stars, last pushed 2d ago), licensed Apache-2.0. It adds 92 tokens to every session and 678 once invoked, about $0.0005 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 2026-09-03.
Other agents, from other repositories
audit-ecosystem
Audits MCP servers, plugins, and hooks against expert knowledge. Dispatched by /claudit during Phase 2.
audit-global
Audits global Claude Code configuration (/.claude/) against expert knowledge. Dispatched by /claudit during Phase 2.
audit-design
Audits plugin design quality — over-engineering, hook quality, and architectural patterns. Dispatched by /hone during Phase 2.
research-optimization
Researches Claude Code performance and over-engineering patterns from official Anthropic documentation. Dispatched by /claudit during Phase 1.
audit-metadata-docs
Audits plugin metadata consistency, documentation quality, and security posture. Dispatched by /hone during Phase 2.
audit-structure
Audits plugin directory layout and file compliance against Claude Code plugin spec. Dispatched by /hone during Phase 2.