Claude for Legal is a collection of AI agents, skills, and data connectors for legal work such as commercial, privacy, employment, litigation, regulatory, and intellectual-property matters. Lawyers and legal teams use it through Claude Cowork, Claude Code, or the Claude Managed Agents API, with attorney review required for every output. The catalogue entries are its workflow plugins, skills, agents, and connectors.
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 skills add anthropics/claude-for-legal --skill build-guidegit clone --depth 1 https://github.com/anthropics/claude-for-legalWrote 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/skills/anthropics/claude-for-legal/build-guide)<a href="https://agentmods.dev/skills/anthropics/claude-for-legal/build-guide"><img src="https://agentmods.dev/badge/skills/anthropics/claude-for-legal/build-guide/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/skills/anthropics/claude-for-legal/build-guide"><img src="https://agentmods.dev/badge/skills/anthropics/claude-for-legal/build-guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
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 | $0.00082 | $0.03392 |
| Opus 5.5 | $0.00033 | $0.01357 |
| Sonnet 5.5 | $0.00016 | $0.00678 |
| Haiku 4.5 | $0.00008 | $0.00339 |
Grade A, and why
build-guide 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 24d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- build-guide — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/build-guide
- Load
~/.claude/plugins/config/claude-for-legal/legal-clinic/CLAUDE.md→ role (must be Supervising attorney), practice areas, jurisdiction. - Use the workflow below.
- If the user is not the supervising attorney, stop and redirect (students run
/legal-clinic:ramp). - Walk through: practice area → intake questions → pedagogy posture → review gates → cross-plugin checks → local rules.
- Write
~/.claude/plugins/config/claude-for-legal/legal-clinic/guides/<practice-area>.md. Create theguides/directory if needed. - Offer a test run — run
/legal-clinic:draftunder the configured posture so the supervisor sees what a student sees.
/legal-clinic:build-guide
Multiple guides are fine — one per practice area. Re-run this command to revise. Edit the guide file directly for quick changes.
Build Guide: Supervisor-Authored Practice-Area Guide
Purpose
The supervisor guide is the dial that turns student-facing skills from "get the work done" into "teach the student to do the work." Every student-facing skill in this plugin reads the guide before producing output: intake asks the questions the supervisor wants asked, drafting skills pick a pedagogy posture (assist / guide / teach), review gates route to the supervisor on the items the supervisor cares about, and cross-plugin checks wrap other-plugin skills in a supervision layer.
This skill helps a supervisor author that guide in 5-10 minutes per practice area. The guide is plain markdown at a well-known path — edit it by hand anytime.
Audience: the supervising attorney. Not students. Students run /legal-clinic:ramp and then the student-facing skills; they don't author guides.
Work-product header
Every output from this skill is a supervisor-facing configuration artifact, not student work product. Do NOT prepend [AI-ASSISTED DRAFT — requires student analysis and attorney review] to the output of this skill — that label is for student outputs. The guide file this skill writes is a supervisor configuration document; it sits next to CLAUDE.md in the plugin config directory, not in a matter workspace.
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.
- 24d ago First seen · 252 lines · 82 tokens per session scan A df13c3ee9012
build-guide is a skill published in the GitHub repository anthropics/claude-for-legal (9,706 stars, last pushed 3d ago), licensed Apache-2.0. It adds 82 tokens to every session and 3,392 once invoked, about $0.0003 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 2026-09-23.
Other skills, from other repositories
mqc-legal-courseware-master
A legal-courseware tool that combines legal charts, explanations, source text, and case notes into editable presentation pages. It uses a fixed grid and can export pages for copying into a lawyer's presentation.
policy-qa
Triage loop for inbound HR policy questions. Classifies each new question from the HR inbox as answerable from the documented Notion policy library or as needing HR's judgment, drafts a grounded Gmail reply for the former, and escalates the latter — anything ambiguous, legal, personal, or compensation-related — to…
bar-prep-questions-bossmann007
Questões de preparação para o Exame de Ordem (OAB) — 1ª fase (objetiva) ou 2ª fase (peça/discursiva), com foco nas matérias fracas do aluno. Rastreia erros e volta aos padrões. Use quando o usuário disser "prova da OAB", "questões de 1ª fase", "peça prática", ou "me teste pra Ordem".
irac-practice-bossmann007
Corrige uma peça/parecer no método IRAC (ou estrutura equivalente) quanto a estrutura, identificação de teses, precisão de fundamentação, profundidade de análise e organização. NÃO reescreve o texto nem mostra resposta-modelo; rastreia padrões entre sessões. Use quando o usuário disser "corrige meu IRAC", "avalia meu…
common-law-simulation-negotiation
Anwalt oder Mandant will UK/US-Vertragsverhandlung oder Mandantengespraech simulieren und False-Friends-Lernkurve absolvieren. Prüfraster Verhandlungs-Simulation Issue-List-Erstellung Mandanten-Erklärung. Output Simulations-Szenario Verhandlungs-Script Lern-Feedback. Abgrenzung zu common-law-quality-gate (Qualitaet)…
case-brief
Resume um julgado/acórdão no seu formato preferido. Em modo sabatina, faz o aluno afirmar a tese/ementa primeiro. Use quando o usuário disser "resume [julgado]", "qual a tese de", "resumo de acórdão", ou colar o inteiro teor de uma decisão.