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 demand-receivedgit 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/demand-received)<a href="https://agentmods.dev/skills/anthropics/claude-for-legal/demand-received"><img src="https://agentmods.dev/badge/skills/anthropics/claude-for-legal/demand-received/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/demand-received"><img src="https://agentmods.dev/badge/skills/anthropics/claude-for-legal/demand-received.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
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 | $0.00072 | $0.03095 |
| Opus 5.5 | $0.00029 | $0.01238 |
| Sonnet 5 | $0.00014 | $0.00619 |
| Haiku 4.5 | $0.00007 | $0.00310 |
Grade A, and why
demand-received 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 3d 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 — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/demand-received
- Read the incoming document from provided path.
- Load
~/.claude/plugins/config/claude-for-legal/litigation-legal/matters/_log.yamlfor portfolio cross-check. - Load
~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md→ risk calibration, landscape, demand-letter practice. - Follow the workflow and reference below.
- Extract fields; cross-check portfolio; assess merit; present options with recommendation.
- Write
~/.claude/plugins/config/claude-for-legal/litigation-legal/inbound/[slug]/triage.md. Copy or link incoming to~/.claude/plugins/config/claude-for-legal/litigation-legal/inbound/[slug]/incoming.[ext]. - Hand off per user choice:
- Create matter →
matter-intakepre-populated - Respond with counter-demand →
demand-intakepre-populated - Link to existing matter → update
related_mattersin log - Standalone → no further action
- Create matter →
Demand Received
Purpose
Inbound demand letters are the bread and butter of an in-house litigation practice. A small fraction need escalation; most can be handled with a structured response or a holding letter. The failure mode is treating them all alike. This skill triages, cross-checks the portfolio, and produces options.
Load context
- The incoming document (user provides path or drops it in-session)
~/.claude/plugins/config/claude-for-legal/litigation-legal/matters/_log.yaml— scan for related matters (same counterparty, overlapping counterparties via entity relationships, or matter type + recent date)~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md→ risk calibration (for merit assessment), landscape (is the sender a frequent adversary?), demand-letter practice (house tone and response defaults)
Workflow
Step 1: Read the demand
Extract from the incoming:
- Sender — entity, signer, counsel (if signed by outside firm)
- Recipient — which entity/person at our company
- Delivery — certified, email, courier (matters for deadline calculation)
- Date received vs. date signed
- Demand type — payment, breach/cure, C&D, preservation, settlement, other
- Specific asks — what they want, by when
- Facts alleged — their version of what happened
- Legal basis — statutes, contract provisions, theories they cite
- Threats — what they say they'll do if we don't comply
- Settlement-communication framing — research the settlement-communication protections applicable in the forum (FRE 408 in federal, the state equivalent otherwise). Note whether the demand is marked as a settlement communication, but remember: protection attaches from conduct and context, not merely from labeling. Capture both the label (if any) and a first-pass read of whether the substance is in fact a compromise discussion.
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.
- 3d ago First seen · 236 lines · 72 tokens per session scan A f935cf45e84d
demand-received is a skill published in the GitHub repository anthropics/claude-for-legal (9,529 stars, last pushed yesterday), licensed Apache-2.0. It adds 72 tokens to every session and 3,095 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
specification-writing
A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.
regulatory-research-fallback
Fallback workflow for regulatory research when web extraction tools fail on government PDFs.
x-scorecard
OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.
memstack-business-gdpr
Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…
navigate-patent-classification
Traverse IPC/CPC-like classification neighborhoods to expand or delimit a technical patent domain.