policy-starter

policy-starter is a skill for Claude Code from anthropics/claude-for-legal. It costs 88 tokens per session (3,714 once invoked), scanned A, original, Apache-2.0.

A research-and-drafting tool for creating an organisation's AI usage policy from published example policies and guidance. The result is a draft for lawyer review and adoption, not a final policy.

In plain words
What is it for?
Use it to draft or update an AI policy, select the sections it should cover, collect relevant sources, and prepare an adoption checklist.
Why use it?
Writing an AI policy from scratch requires researching laws, professional guidance, and the organisation's actual use of AI. This structures that research and marks decisions that need review.

Skill for Claude Code ✓ vendor

Written for Claude Code: argument-hint in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md.

Part of the ai-governance-legal plugin — 10 skills, 2 MCP servers shipped together

Good fit Use it to draft or update an AI policy, select the sections it should cover, collect relevant sources, and prepare an adoption checklist.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/anthropics/claude-for-legal/policy-starter
About the project

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.

anthropics/claude-for-legal · 9,433 stars · on GitHub

Install

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.

Any agent
npx skills add anthropics/claude-for-legal --skill policy-starter
Clone the repo
git clone --depth 1 https://github.com/anthropics/claude-for-legal

Made for: Claude Code.

Or install ai-governance-legal, the plugin that ships this one along with the rest of its 10 skills, 2 MCP servers.

Wrote 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.

agentmods badge for policy-starter

README.md
[![agentmods](https://agentmods.dev/badge/skills/anthropics/claude-for-legal/policy-starter/github.svg)](https://agentmods.dev/skills/anthropics/claude-for-legal/policy-starter)
Your own site
<a href="https://agentmods.dev/skills/anthropics/claude-for-legal/policy-starter"><img src="https://agentmods.dev/badge/skills/anthropics/claude-for-legal/policy-starter/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.

agentmods 80×15 button for policy-starter

Your own site · 80×15
<a href="https://agentmods.dev/skills/anthropics/claude-for-legal/policy-starter"><img src="https://agentmods.dev/badge/skills/anthropics/claude-for-legal/policy-starter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,714 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket pass 12 Jun 2026
  • Snyk warn 12 Jun 2026
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Rogue Agent · line 33
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00088 $0.03714
Opus 5 $0.00044 $0.01857
Sonnet 5 $0.00018 $0.00743
Haiku 4.5 $0.00009 $0.00371

Measured 13d ago against content hash 3c31c4ffd95a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

policy-starter 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 13d 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

ai-governance-legal/skills/policy-starter/SKILL.md · 263 lines

How it starts

The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/policy-starter

  1. Read ~/.claude/plugins/config/claude-for-legal/ai-governance-legal/CLAUDE.md. If the practice profile is unpopulated, stop and direct to /ai-governance-legal:cold-start-interview.
  2. Use the framework below.
  3. Run the scope interview — which sections does the policy need to cover, who's the audience, what's the deployment context. Do not skip to drafting.
  4. Web search for the current published model policies and guidance relevant to the deployment context (ABA, state bars, ILTA, CLOC, NIST, peer-firm / peer-company policies, current state AI laws, EU AI Act, sector regulators as applicable).
  5. Draft the selected sections, sourced from the model policies, with [review] flags on every choice point and [review] open questions at the bottom of each section.
  6. Output with the draft header ("DRAFT FOR INTERNAL LEGAL REVIEW — NOT FOR DISTRIBUTION"), the sources block, the reviewer note, and the adoption checklist.
  7. Close with the next-steps decision tree.
/ai-governance-legal:policy-starter
/ai-governance-legal:policy-starter "we need an AI policy for our 30-lawyer firm"
/ai-governance-legal:policy-starter "update our existing policy for the 2026 state AI laws"

Matter context

Matter context. Check ## Matter workspaces in the practice-level CLAUDE.md. If Enabled is (the default for in-house users), skip the rest of this paragraph — skills use practice-level context and the matter machinery is invisible. If enabled and there is no active matter, ask: "Which matter is this for? Run /ai-governance-legal:matter-workspace switch <slug> or say practice-level." Load the active matter's matter.md for matter-specific context and overrides. Write outputs to the matter folder at ~/.claude/plugins/config/claude-for-legal/ai-governance-legal/matters/<matter-slug>/. Never read another matter's files unless Cross-matter context is on.


Purpose

A lot of firms and in-house teams don't have a written AI usage policy yet, or are running on a 2024-vintage one that doesn't mention the state AI laws, the EU AI Act implementing acts, the 2025 COPPA amendments, or what they actually ended up doing with Copilot and Claude for Work. This skill produces a draft policy to bring to the decision-maker — GC, managing partner, executive committee, board, head of IT, head of HR — not a finished policy to circulate.

Read the full file on GitHub · 263 lines

Changes

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.

  1. 13d ago First seen · 263 lines · 88 tokens per session scan A 3c31c4ffd95a

Subscribe to this mod's changes

policy-starter is a skill published in the GitHub repository anthropics/claude-for-legal (9,433 stars, last pushed 21d ago), licensed Apache-2.0. It adds 88 tokens to every session and 3,714 once invoked, about $0.0004 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.

Related

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.

wanshuiyin/Auto-claude-code-research-in-sleep · 49 tokens

regulatory-research-fallback

Fallback workflow for regulatory research when web extraction tools fail on government PDFs.

HKUDS/OpenSpace · 20 tokens

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.

x-cmd/x-cmd · 57 tokens

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.

Klotzkette/claude-fuer-deutsches-recht · 69 tokens

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…

cwinvestments/memstack · 121 tokens

nda-review

Use when the user uploads or pastes a non-disclosure agreement and asks for review, redline, risk assessment, or a recommendation on whether to sign. Identifies missing standard protections, one-sided or unusual provisions, and operational issues; produces a structured report with severity ratings and citations to…

LegalQuants/lq-ai · 79 tokens