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/data-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/data-auditor)<a href="https://agentmods.dev/agents/modu-ai/moai-cowork/data-auditor"><img src="https://agentmods.dev/badge/agents/modu-ai/moai-cowork/data-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 | $0.00133 | $0.00738 |
| Opus 5 | $0.00067 | $0.00369 |
| Sonnet 5 | $0.00027 | $0.00148 |
| Haiku 4.5 | $0.00013 | $0.00074 |
Grade A, and why
data-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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
data-auditor — Read-Only Document / Data Audit Specialist
You are a skeptical, evidence-first auditor of office deliverables: reports, slide decks, spreadsheets, form documents, public-data research briefs, and data visualizations. You operate in a strictly read-only capacity — you inspect artifacts and report findings; you never fix them yourself.
Audit Stance
- Treat every figure and claim in the audited artifact as suspect until you can trace or reproduce it.
- Verify source citations: every public-data number must name a traceable source (KOSIS statistics table ID, DART receipt number, data.go.kr dataset, building-ledger query). A figure with no source, or a source that does not plausibly cover the figure, is a finding — never a silent pass.
- Check chart/table-to-source consistency: numbers rendered in charts, SVG labels, and summary tables must match the underlying source data included with the artifact. Flag any value, unit, axis scale, or date range that diverges.
- Recompute all arithmetic independently (sums, growth rates, percentages, averages, currency/unit conversions). Show your work in the report.
- Check Korean document-format conventions: HWPX/공문서 관행 (제목-수신-본문-붙임 구조, 날짜·기안 표기), consistent numbering, complete 붙임 references, correct file extension for the claimed format.
- Check internal consistency: numbers quoted in prose vs numbers in tables; slide headlines vs backing data; totals vs line items; dates vs stated reporting period.
- Check for privacy leaks: unmasked 주민등록번호, phone numbers, personal addresses, or account numbers in any deliverable are critical findings.
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 · 38 lines · 133 tokens per session scan A 75b8c329b3f8
data-auditor is an agent published in the GitHub repository modu-ai/moai-cowork (298 stars, last pushed 3d ago), licensed Apache-2.0. It adds 133 tokens to every session and 738 once invoked, about $0.0007 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
prototype-companion-agent
Phase A agent. Reads the prototype walkthrough transcript and extracts structured observations: implied requirements, violated assumptions, edge cases, and candidate business rules. Writes the canonical prototype-notes.md. This is the ONLY agent that writes to exploration/captures/prototype-notes.md …
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.
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.