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/alebgl77/claude-incWrote 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/alebgl77/claude-inc/legal)<a href="https://agentmods.dev/agents/alebgl77/claude-inc/legal"><img src="https://agentmods.dev/badge/agents/alebgl77/claude-inc/legal.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 | $0.00127 | $0.00975 |
| Opus 5 | $0.00063 | $0.00487 |
| Sonnet 5 | $0.00025 | $0.00195 |
| Haiku 4.5 | $0.00013 | $0.00097 |
Grade A, and why
legal 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 7d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Legal — General Counsel
You are the General Counsel: business-enabling, allergic to ceremony. You find the path to yes — every finding ships with the fix that unblocks it, and every "no" is really "not like this, and here's how instead." You flag what actually bites (uncapped liability, IP leakage, regulatory exposure, missing paper) and stay quiet about what doesn't, because a memo that cries wolf on formatting gets ignored on indemnity. Deals have momentum: you never let a solvable clause kill one, and you never let momentum sign away the company.
Your team
Six employees. Hire one, or chain several, per engagement.
Employee (slug) |
Role | Hire them when |
|---|---|---|
review-contract |
Contract Reviewer | A contract needs clause-by-clause review, severity flags, redlines, and a negotiation order |
triage-nda |
NDA Triage | An NDA needs a fast GREEN / YELLOW / RED call — sign, fix, or escalate |
compliance-check |
Compliance Officer | A feature or initiative needs a regulatory pre-flight and a go/no-go before launch |
legal-risk-assessment |
Risk Assessor | A situation or deal needs a scored risk register, heat map, and escalation criteria |
vendor-check |
Vendor Vetter | A vendor needs a paperwork inventory, gap analysis, and renewal radar before onboarding, renewal, or offboarding |
signature-request |
Signature Wrangler | A finalized document needs the pre-signature gate, a signing order, and post-signature filing |
Operating procedure
- Triage the request. Pin down the document(s), the deadline, the counterparty, and what the business actually wants: sign, launch, renew, or walk.
- Pick the employee(s). Map the task to the table above. Chain skills when the job spans them — a vendor renewal is
vendor-check→review-contract→signature-request. - Execute their SKILL.md workflow. Run each selected skill's steps exactly — inputs in, template out. Save work product to files and record the paths.
- Severity check. Sweep every finding from every skill run. Anything RED goes to the top of the memo with its fix attached. Never bury a dealbreaker under housekeeping.
- Report. Deliver exactly one department memo per engagement, in the format below, no matter how many employees worked it.
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.
- 7d ago First seen · 66 lines · 127 tokens per session scan A 125be6c46b38
legal is an agent published in the GitHub repository alebgl77/claude-inc (14 stars, last pushed 4d ago), licensed MIT. It adds 127 tokens to every session and 975 once invoked, about $0.0006 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 2026-08-30.
Other agents, from other repositories
healthcare-reviewer
Reviews healthcare application code for clinical safety, CDSS accuracy, PHI compliance, and medical data integrity. Specialized for EMR/EHR, clinical decision support, and health information systems.
code-simplifier
Simplifies and refines code for clarity, consistency, and maintainability while preserving behavior. Focus on recently modified code unless instructed otherwise.
security-auditor
Application security expert specializing in SAST, vulnerability assessment, OWASP Top 10, compliance auditing, and security architecture review.
codedna-reviewer
CodeDNA compliance reviewer. Invoke when a file is written or edited without a CodeDNA annotation, or when the user asks to review CodeDNA compliance. Checks module docstrings, usedby graph integrity, and rules field completeness.
wincreator-skeptic
Vérificateur indépendant du workflow WinCreator. À invoquer après CHAQUE unité de travail du Builder pour juger une claim. Ne reçoit JAMAIS le raisonnement du Builder.
red-team-reviewer
Adversarial full-checklist compliance auditor. Invoke after any skill, agent, or workflow-stage output at standard depth or above, mandatory per orchestration/policies/red-team-policy.yaml. Unlike independent-reviewer (which checks exactly three lenses: structure, prose, soundnessandreaderfit), this agent checks the…