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 invention-intakegit 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/invention-intake)<a href="https://agentmods.dev/skills/anthropics/claude-for-legal/invention-intake"><img src="https://agentmods.dev/badge/skills/anthropics/claude-for-legal/invention-intake/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/invention-intake"><img src="https://agentmods.dev/badge/skills/anthropics/claude-for-legal/invention-intake.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 | $0.00061 | $0.05265 |
| Opus 5.5 | $0.00024 | $0.02106 |
| Sonnet 5 | $0.00012 | $0.01053 |
| Haiku 4.5 | $0.00006 | $0.00526 |
Grade B, and why
invention-intake scanned grade B with 1 finding 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.
Tells the agent never to refusemediumAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
> When the practice profile includes non-US jurisdictions: "This §101 screen is US-only. If you file internationally, the eligibility posture may be different — particularly for software, AI/ML, and business methods, whi Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 473 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/invention-intake
This is a first-pass screen by a non-specialist, not a patentability opinion. The screen never concludes that an invention is patentable — it concludes that it passes the initial screen and warrants a prior-art search and registered-practitioner review, that it needs more information, or that it hits a disqualifier. A prior-art search is a separate step; this skill does not do one.
Instructions
- Read
~/.claude/plugins/config/claude-for-legal/ip-legal/CLAUDE.md. If it contains[PLACEHOLDER], stop and direct to/ip-legal:cold-start-interview. If the practice profile shows trademark- or copyright-only (no patent practice), say so and route the user elsewhere — this is the wrong tool. - Follow the workflow below.
- Run intake. If the user pasted or uploaded a disclosure, read it. If not, ask the seven intake questions (what / problem / differences / inventors / public disclosure / status / technology area) in one batch and wait.
- Run the six screens: novelty signals, obviousness flags, § 101 eligibility, public disclosure / bar dates, detectability, strategic value. Each screen gets a ✓ / 🟡 / 🔴 verdict with one-line reasoning.
- Write the invention screen memo to the matter folder (if a matter is active) or the practice outputs folder. Apply the work-product header per role.
- Bottom-line verdict: PURSUE (schedule prior-art search and attorney review) / INVESTIGATE (needs more info on a specific open item) / DECLINE (state the concrete reason). Never say "patentable."
- Close with the decision tree (prior-art search / inventor follow-up / specialist review / decline + thank-you / trade-secret route) and the non-lawyer gate if the role is non-lawyer.
- If the screen hit a within-one-year US disclosure or any public disclosure with foreign rights in scope, flag at the top: time-sensitive.
This skill never concludes that an invention is patentable. If uncertain, flag — a registered patent attorney or agent decides.
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 · 473 lines · 61 tokens per session scan B beb7db467fd4
invention-intake 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 61 tokens to every session and 5,265 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-23.
Other skills, from other repositories
analytical-method-validation
Plan, execute, and document validation, verification, and transfer of analytical procedures under the governing framework - ICH Q2(R2) and Q14, USP / / , ICH M10 bioanalytical, CLSI EP, or ISO/IEC 17025. Use for HPLC, LC-MS/MS, GC, CE, ICP-MS, dissolution, qNMR, qPCR, NIR, and ligand binding or cell-based assays…
nature-paper-to-patent
A workflow for turning scientific papers, theses, reports, code, figures, or inventor notes into evidence-based Chinese invention-patent drafts and technical disclosures. A technical disclosure is a document that explains an invention to a patent attorney.
auditing-part11-trails
Generates and verifies 21 CFR Part 11-style audit trails — who/what/when, electronic signatures, and tamper-evidence — for OpenMed pipelines in GxP and clinical-trial (GCP) settings. Use when the user runs OpenMed in a regulated/validated environment and needs an attributable, time-stamped, tamper-evident record of…
generating-synthetic-surrogates
Replace detected PHI with realistic, type-matched fake values in OpenMed so clinical notes stay readable and parseable instead of full of [REDACTED] markers. Use when the user wants surrogate names, MRNs, addresses, or dates rather than opaque masks, needs consistent fake identities across a document, must keep notes…
shifting-clinical-dates
Apply consistent per-patient date shifting in OpenMed that preserves intervals between events while satisfying HIPAA Safe Harbor's date rule. Use when the user needs to de-identify dates but keep temporal structure for research, shift all dates by the same offset per patient, preserve days-between-events for survival…
fda-database
Query openFDA API for drugs, devices, adverse events, recalls, regulatory submissions (510k, PMA), substance identification (UNII), for FDA regulatory data analysis and safety research.