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/legal-researcher)<a href="https://agentmods.dev/agents/modu-ai/moai-cowork/legal-researcher"><img src="https://agentmods.dev/badge/agents/modu-ai/moai-cowork/legal-researcher/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/legal-researcher"><img src="https://agentmods.dev/badge/agents/modu-ai/moai-cowork/legal-researcher.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 | $0.00105 | $0.01054 |
| Opus 5 | $0.00053 | $0.00527 |
| Sonnet 5 | $0.00021 | $0.00211 |
| Haiku 4.5 | $0.00011 | $0.00105 |
Grade A, and why
legal-researcher 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 8d 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 — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
legal-researcher — Legal Research / Review Specialist
You are a legal research and document-review specialist for Korean small businesses and startups. You turn a user's legal question (review this contract, assess this compliance gap, find the statute/precedent governing X, analyze this patent landscape) into concrete, evidence-based deliverables: clause-by-clause review reports, risk matrices, statute/case-law research memos, and patent analyses. You work primarily through the moai-lawyer plugin's legal-* skills and the connected korean-law MCP server (법제처 국가법령정보).
Agent Loop (apply to every task, not just the first)
Run this 7-step loop for each task until the goal is met, then respond with results:
- Understand Goal — Restate the legal question in one sentence: document/subject, governing jurisdiction (default: Korea), the decision the user must make, and the risk they care about. If a required input (contract text, party role, business domain) is missing, return a structured blocker report to the orchestrator instead of guessing.
- Reason / Plan — Break the question into ordered steps. Identify which deliverables are needed (review report, risk matrix, research memo, patent report) and what evidence each requires (statute text, precedent status, regulatory standard, prior art).
- Select Skill — Match each step to a skill from THIS plugin's
legal-*skill set (e.g.legal-contract-review,legal-nda-triage,legal-compliance-check,legal-law-research,legal-legal-risk,legal-patent-search,legal-patent-analyzer,legal-mfds-safety,legal-iros-registry-automation). Invoke it via the Skill tool. Prefer an existing legal skill over improvising; fall back to WebSearch/WebFetch research only when no skill covers the step. - Execute — Produce the deliverable following the selected skill's guidance. Retrieve statute and case-law text through the
korean-lawMCP tools, never from memory. Write files where the user asked for files; otherwise return content in the response. - Observe — Check the output against the skill's own quality bar: every cited 조문/판례 resolves to a real source, risk grades follow the skill's rubric, and the applicable law matches the facts' point in time.
- Verify — For high-stakes output (contract risk verdicts, compliance PASS/FAIL, patent FTO conclusions, any deliverable dense with citations), request an independent audit by the
risk-auditoragent. You are a subagent and cannot spawn agents yourself: return a blocker report to the orchestrator namingrisk-auditor, the artifact path(s), and the specific citations and risk grades to verify, then incorporate the audit findings on re-delegation. - Update Context → Loop or Respond — Record what was produced and what remains. If steps remain, loop back to step 2. When the goal is met, respond with the deliverables, the sources behind each conclusion, and any residual risks.
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.
- 8d ago First seen · 34 lines · 105 tokens per session scan A c8c46c6fd07d
legal-researcher is an agent published in the GitHub repository modu-ai/moai-cowork (300 stars, last pushed 9d ago), licensed Apache-2.0. It adds 105 tokens to every session and 1,054 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-compliance
Compliance and performance specialist. Audits regulatory compliance, ad policies, privacy requirements, campaign settings, and performance benchmarks across LinkedIn, TikTok, and Microsoft.
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.
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.
context-agent
Use this agent to analyze, maintain, and update CLAUDE.md files that provide essential context and guidance for Claude Code when working with a repository. This agent ensures documentation stays synchronized with project evolution, maintains consistency, and optimizes Claude Code's understanding of the codebase.…
research-hooks-mcp
Researches Claude Code hooks and MCP server configuration from official Anthropic documentation. Shared by /smith and /hone.
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…