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 case-briefgit 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/case-brief)<a href="https://agentmods.dev/skills/anthropics/claude-for-legal/case-brief"><img src="https://agentmods.dev/badge/skills/anthropics/claude-for-legal/case-brief/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/case-brief"><img src="https://agentmods.dev/badge/skills/anthropics/claude-for-legal/case-brief.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 | $0.00052 | $0.01498 |
| Opus 5.5 | $0.00021 | $0.00599 |
| Sonnet 5 | $0.00010 | $0.00300 |
| Haiku 4.5 | $0.00005 | $0.00150 |
Grade A, and why
case-brief 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 6d 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:
- case-brief — 100% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/case-brief
- Load
~/.claude/plugins/config/claude-for-legal/law-student/CLAUDE.md→ outline/brief preferences. - Apply the workflow below.
- Brief in the student's format. If drill-me mode: ask the student to state the holding first.
Purpose
A case brief is a tool for remembering what a case does. This skill makes one in your format — the format you'll actually use in your outline.
Confidence discipline
Case briefs state holdings, rules, and reasoning. Getting them wrong turns your outline into a false map. The rule for this skill:
- If you paste the case text: I extract holding/rule/reasoning from what's in front of me. Confident.
- If you only give a case name: I brief from knowledge. Worth a lot less. I flag every line I'm not sure about with
[UNCERTAIN: specific reason], and I strongly recommend you confirm against the actual case before putting the brief in your outline. If I don't know the case well enough, I say so. - If the case has famous-but-contested interpretations: I give the majority read and
[VERIFY: check your casebook and professor's framing].
A brief built on my guess and your good faith is worse than no brief. Better to err toward "I'm not sure — read it yourself" than to invent.
Load context
~/.claude/plugins/config/claude-for-legal/law-student/CLAUDE.md → outline/brief preferences (format, depth), learning style.
The "don't brief it for me" rule (hard rule)
A brief you didn't write is a brief you won't remember. Every mode of this skill defaults to scaffolding the student's brief-writing, not to writing the brief.
What this skill will do in every mode:
- Ask the student what they already got from reading: the facts, the issue, the holding as they understand it.
- Provide the blank template in their preferred format (headings for Facts, Issue, Holding, Reasoning, Rule, Notes).
- Ask pointed follow-ups on whichever section is thin: "What were the key facts the court actually relied on?", "What's the narrow issue vs. the broader question?", "Why did the court reject the dissent's framing?"
- If the student pastes the case text, extract verbatim the court's own language for holding and reasoning — that is not writing-for-them; that is pointing at what the case says.
- Flag confused or wrong understandings: "You said the holding is X. The court's actual language is closer to Y. Which one is the rule you'll carry into your outline?"
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.
- 6d ago First seen · 109 lines · 52 tokens per session scan A 51667ab84e4e
case-brief is a skill published in the GitHub repository anthropics/claude-for-legal (9,544 stars, last pushed 4d ago), licensed Apache-2.0. It adds 52 tokens to every session and 1,498 once invoked, about $0.0002 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
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…
learn-law-with-rohas
Acts as an interactive legal tutor for learning a law, legal subject, doctrine, judgment, procedure, or legal concept. Builds a learning path around the user's topic and level, teaches concepts step by step, uses examples and hypotheticals, asks questions and quizzes, explains mistakes, adapts difficulty, revises weak…
legal-explainer
Explains laws, legal concepts, judgments, clauses, rights, obligations, procedures, and legal positions in clear plain language without losing legal accuracy. Use when a user asks "what does this mean?", "explain this law simply", "explain this clause", "what does this judgment actually say", "explain this to a…
patsnap-ip-innovation-courses
Patsnap IP & Innovation Courses MCP for AI agents. A one-stop learning entry for courses, course details, and training materials on IP and innovation. It helps teams build a structured understanding of patents, search, analysis, and business use while lowering the learning barrier for new users. It is useful for…
educational-documentation
IEP writing, IDEA compliance, SMART goal frameworks, progress monitoring methods, and parent-friendly reporting.
classroom-ai-ethics
Classroom AI ethics — FERPA, COPPA, age-appropriate AI literacy framing, bias-discussion frameworks.