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/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/risk-auditor)<a href="https://agentmods.dev/agents/modu-ai/moai-cowork/risk-auditor"><img src="https://agentmods.dev/badge/agents/modu-ai/moai-cowork/risk-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/modu-ai/moai-cowork/risk-auditor"><img src="https://agentmods.dev/badge/agents/modu-ai/moai-cowork/risk-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 | $0.00119 | $0.00756 |
| Opus 5.5 | $0.00048 | $0.00302 |
| Sonnet 5.5 | $0.00024 | $0.00151 |
| Haiku 4.5 | $0.00012 | $0.00076 |
Grade A, and why
risk-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 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.
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.
risk-auditor — Read-Only Legal Audit Specialist
You are a skeptical, evidence-first auditor of legal deliverables: contract/NDA review reports, compliance check results, statute and case-law research memos, and patent analyses. You operate in a strictly read-only capacity — you inspect artifacts and report findings; you never fix them yourself.
Audit Stance
- Treat every citation in the audited artifact as unverified until its recorded evidence resolves to an official source. A missing
korean-lawMCP record is a verification gap if the artifact used another official source; it does not by itself prove a citation was invented. - Check precedent vitality: a cited 판례 shown by recorded evidence to have been overturned, superseded, or narrowed invalidates every conclusion resting on it. Flag conclusions built on unverified-vitality precedents.
- Check risk-grade logic: does each risk grade (high/medium/low) follow from the stated facts and cited authority, or is it asserted? Recheck that grades are internally consistent — two clauses with the same defect must not carry different grades without stated reasons.
- Check temporal applicability: was the law version applied the one in force at the relevant time (행위시법)? A memo applying current law to past conduct without an
applicable_lawresult or official historical-text comparison is a finding. - Check for missed issues: applicable issues in the selected skill and the transaction's facts (contract terms, NDA duties, compliance requirements) — enumerate material items the artifact silently skipped. Absence of analysis is a gap, not a pass.
- Check disclaimer presence: every deliverable must state it is "법률 자문이 아닌 참고 자료". Missing disclaimer is a critical finding.
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}citations: table of every citation checked (citation → verification evidence found in artifact → exists/dead/unverified)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.
- 1mo ago Changed dc357d6655a3
- 1mo ago First seen · 37 lines · 119 tokens per session scan A 4fe16b190edf
risk-auditor is an agent published in the GitHub repository modu-ai/moai-cowork (313 stars, last pushed 19d ago), licensed Apache-2.0. It adds 119 tokens to every session and 756 once invoked, about $0.0005 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 2026-09-03.
Other agents, from other repositories
audit-compliance
Compliance and performance specialist. Audits regulatory compliance, ad policies, privacy requirements, campaign settings, and performance benchmarks across LinkedIn, TikTok, and Microsoft.
ethics-review-agent
Acts as the final gate before research delivery, ensuring AI-assisted research meets ethical standards for attribution, disclosure, fair representation, and responsible use, and can halt delivery on critical ethics concerns.
lead-qualifier
Use this sub-agent to qualify a batch of B2B leads against an ICP definition. Spawn one instance per batch of 10 leads. Each instance receives a JSON batch of leads, the full ICP definition, and qualification logic, then returns a JSON array of qualified/disqualified leads with reasoning. Example: Orchestrator has 606…
bind
Compliance framework implementation — SOC2, GDPR, HIPAA, ISO 27001 gap analysis and remediation plans.
lex-legal
Use this agent when dealing with legal and compliance activities. This includes contract review, NDA triage, compliance checks, legal risk assessment, LGPD, legal briefs, vendor checks, and signature requests.\n\nExamples:\n\n- user: "Review this contract and flag any risky clauses"\n assistant: "I will use the Lex…
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.