New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Official agent skill

Policy Monitor

by anthropics in anthropics/claude-for-legal

Keep the privacy policy current with practice. An agent skill from anthropics/claude-for-legal.

OfficialApache-2.0Auto-check passedLegal & Compliance

Install Policy Monitor

skills CLI
$ npx skills add anthropics/claude-for-legal --skill policy-monitor -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install anthropics/claude-for-legal policy-monitor --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/anthropics/claude-for-legal.git skills-src && mkdir -p .claude/skills && cp -r skills-src/privacy-legal/skills/policy-monitor .claude/skills/policy-monitor && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
policy-monitor
GitHub stars
9.6k
Used in
2 other repos
Token cost
~4.5k tokens
SKILL.md length
2,048 words
Files
1
Skills in repo
147
Repo updated
First seen
Licence
Apache-2.0

At a glance

Keep the privacy policy current with practice. An agent skill from anthropics/claude-for-legal.

  • Works in 6 steps: Read… → Run the workflow below. Scan outputs… → For each output: extract approved… → …
  • The user asks does our policy cover this
  • SKILL.md covers Purpose, Load current state, Mode detection and Mode 1: Sweep, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Policy Monitor is an agent skill from anthropics/claude-for-legal, published by the product's own GitHub organization. Keep the privacy policy current with practice. Two modes: weekly sweep of saved PIAs, DPA reviews, and triage results to find policy drift; or direct query for a proposed new practice. Use when the user asks "does our policy cover this", "we want to start doing X — does the policy need updating", "run the policy monitor", "policy sweep", or wants to find where the privacy policy no longer matches what the team actually does.

Its SKILL.md is about 4.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Legal & Compliance, covering Privacy and GDPR. The repository describes itself as: A suite of plugins for legal workflows. The licence is Apache-2.0.

When your agent uses it

  • The user asks does our policy cover this
  • We want to start doing X — does the policy need updating
  • Run the policy monitor
  • Wants to find where the privacy policy no longer matches what the team actually does

Example prompts

  • “does our policy cover this”
  • “we want to start doing X — does the policy need updating”
  • “run the policy monitor”
  • “/policy-monitor”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Read ~/.claude/plugins/config/claude-for-legal/privacy-legal/CLAUDE.md → outputs folder path, policy document, last sweep date.
  2. Run the workflow below. Scan outputs folder for files since last sweep.
  3. For each output: extract approved practices → diff against current policy commitments.
  4. Classify gaps: REQUIRED (policy misrepresents current practice) vs ADVISABLE (policy silent).
  5. For each gap: quote current policy, describe gap, draft suggested language.
  6. Update Last policy sweep date in ~/.claude/plugins/config/claude-for-legal/privacy-legal/CLAUDE.md.

What it can do on your machine

Read from SKILL.md and the folder at commit 4a6c651. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Policy Monitor loads about 4.5k tokens when it runs. Until then it costs about 111 tokens; SKILL.md has 2,048 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~111
When it runs · the whole SKILL.md, loaded when a task matches
~4.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from anthropics/claude-for-legal at commit 4a6c651, republished under its Apache-2.0 licence (© anthropics). 2,048 words, ~4,464 tokens.

Download SKILL.mdSave it as .claude/skills/policy-monitor/SKILL.md (or your agent's skills folder).
name
policy-monitor
description
Keep the privacy policy current with practice. Two modes: weekly sweep of saved PIAs, DPA reviews, and triage results to find policy drift; or direct query for a proposed new practice. Use when the user asks "does our policy cover this", "we want to start doing X — does the policy need updating", "run the policy monitor", "policy sweep", or wants to find where the privacy policy no longer matches what the team actually does.
argument-hint
[describe a proposed new practice — or omit / use --sweep for crawl mode]

/policy-monitor

Sweep mode (no argument or --sweep):

  1. Read ~/.claude/plugins/config/claude-for-legal/privacy-legal/CLAUDE.md → outputs folder path, policy document, last sweep date.
  2. Run the workflow below. Scan outputs folder for files since last sweep.
  3. For each output: extract approved practices → diff against current policy commitments.
  4. Classify gaps: REQUIRED (policy misrepresents current practice) vs ADVISABLE (policy silent).
  5. For each gap: quote current policy, describe gap, draft suggested language.
  6. Update Last policy sweep date in ~/.claude/plugins/config/claude-for-legal/privacy-legal/CLAUDE.md.

Direct query mode (with description argument):

  1. Read ~/.claude/plugins/config/claude-for-legal/privacy-legal/CLAUDE.md → current policy commitments + actual policy document.
  2. Parse proposed practice. Diff against policy: data categories, purposes, third parties, retention, user rights, disclosure.
  3. Output: covered / missing / conflicting + suggested language for each gap + timing recommendation.

Schedule: Set up a recurring reminder in your own scheduler (calendar, task manager, or CI) to run /privacy-legal:policy-monitor weekly. Scheduled execution requires a scheduled-tasks integration, which is not bundled with this plugin.

/privacy-legal:policy-monitor
/privacy-legal:policy-monitor "We want to start using behavioral data to personalize onboarding emails"

Privacy Policy Monitor

Purpose

Privacy policies drift from practice in one direction: practice moves forward, policy stays behind. A PIA approves a new data category. A DPA is signed with a subprocessor not listed anywhere. A triage result marks a new use case conditional with a disclosure requirement that the policy doesn't yet make. Months later, someone reads the policy and it doesn't reflect what actually happens.

This skill catches the drift before it becomes a problem — either by crawling the outputs folder weekly, or by answering the direct question: "we're about to start doing X, what does that mean for the policy?"

The output is always the same: here's the gap, here's the suggested language.

Load current state

Read ~/.claude/plugins/config/claude-for-legal/privacy-legal/CLAUDE.md:

  • ## Who we are → ## Regulatory footprint — the regimes in scope (GDPR, CCPA / CPRA / other state consumer privacy, GLBA, HIPAA, FERPA, COPPA, VPPA, CPNI, etc.)
  • ## Privacy policy commitments — the commitments extracted from the published policy
  • ## Outputs — outputs folder path, policy document location, last sweep date

If ## Outputs contains [PLACEHOLDER]:

"Outputs aren't configured yet. I can still run a direct-query check — describe what you're planning to do and I'll diff it against your current policy. To enable the crawl sweep, run /privacy-legal:cold-start-interview and provide the outputs folder path."

Read the actual privacy policy document from the path in ## Outputs → Privacy policy document. The commitments in the config CLAUDE.md are a summary; the actual document is authoritative for suggesting edits.

Privacy commitments live on multiple surfaces — sweep all of them

The website privacy policy is one surface. Modern privacy programs make binding commitments in at least four more places that regulators actively scrutinize for inconsistencies:

  1. Cookie consent banners / CMPs. The consent management platform promises specific cookie categories and purposes. If the privacy policy says "we use analytics cookies" and the CMP offers "strictly necessary only," there's a conflict. EU DPAs and the FTC have both enforced against CMP misconfigurations.
  2. App store privacy labels. Apple App Privacy (the "nutrition label") and Google Data Safety are self-declared and FTC-enforceable. A company that updates its privacy policy but doesn't update its App Store label has a material, regulator-visible inconsistency. Check: when was the label last updated? Does it match the current policy's data categories, purposes, and sharing?
  3. In-product consent flows. The actual screens where users make data-use choices (onboarding consents, settings toggles, "we've updated our policy" dialogs). The policy says what you do; the consent flow says what the user agreed to. They should match.
  4. Sector-specific notices. GLBA privacy notices, HIPAA NPPs, FERPA directory notices, COPPA direct notices. These have their own update obligations and their own consistency requirements with the general privacy policy. (Detail below under "Sectoral notices.")

Add fields to the practice profile for each surface's location and last-updated date. The sweep checks each against the current policy and flags divergence: "Privacy policy updated [date]. App Store label last updated [earlier date] — may not reflect the new data category. CMP last configured [date] — verify cookie purposes match the policy."

A company with a clean privacy policy and a stale App Store label is a company with an FTC complaint waiting to happen. Sweep the surfaces, not just the document.

Sectoral notices are in scope for this sweep

The website privacy policy is one notice. Federally-regulated practices require a separate, sector-specific notice that the website policy does not substitute for. If ## Regulatory footprint includes any of the following, the sweep diffs practice against that notice in addition to the website policy — or flags its absence if no such notice has been configured:

Footprint entrySectoral notice to diff againstWhat to flag
GLBA / Reg P (financial institution handling NPI)GLBA initial + annual privacy notice (12 C.F.R. Part 1016, or the functional regulator's equivalent)Outputs implying new NPI categories, sharing with non-affiliated third parties, or changes to opt-out mechanics that the Reg P notice doesn't reflect. A DPA signed with an analytics vendor receiving NPI with no matching Reg P notice update is a gap.
HIPAA (covered entity or BA)Notice of Privacy Practices (45 C.F.R. § 164.520)Outputs implying new uses or disclosures, new routine categories, or changes to patient-rights mechanics. A BAA signed with a new subcontractor flowing PHI with no matching NPP refresh is a gap.
FERPA (school or school service provider)Annual directory-information / rights notice (34 C.F.R. § 99.37)Outputs implying new disclosure categories to service providers under the school-official exception, new directory-information elements, or changes that implicate parental-consent flow-through.
COPPA (operator of service directed to children <13)Direct notice to parents + online notice (16 C.F.R. § 312.4)Outputs implying new data categories collected from children, new third-party disclosures, or changes to the verifiable-parental-consent mechanic.
VPPA / CPNI / DPPA / other sectoralThe regime's specific notice or consent regimeProcessing activities the regime restricts that aren't reflected in the configured notice.

If no sectoral notice is configured for a regime in the footprint, surface this as a standing gap on every sweep, not a one-time finding. The sweep output should include:

Sectoral notice coverage:

  • [regime]: [configured notice path + last updated, or "NOT CONFIGURED — flag each sweep until resolved"]

If the sweep cannot locate the sectoral notice, say so explicitly — do not silently default to diffing only against the website policy. A fintech DPO relying on a policy-monitor sweep that ignored GLBA would ship with an outdated regulator-facing notice and no warning. Surface the gap loudly.

Ask the user if the footprint is ambiguous. If ## Regulatory footprint says "GDPR / CCPA" but the outputs scan surfaces PHI, NPI, or student data categories, surface the footprint-vs-practice mismatch before proceeding: "Your footprint doesn't list [GLBA / HIPAA / FERPA / COPPA] but this sweep is looking at outputs that involve [category]. Should this regime be added to the footprint, and is there a sectoral notice to diff against?"

Mode detection

Sweep mode: No argument, --sweep, or triggered by schedule. → Scan the outputs folder. Diff all outputs since last sweep against current policy.

Direct query mode: User provides a description of a proposed new practice. → Diff that practice against current policy. Suggest updates.

Mode 1: Sweep

Determine scope

Read ## Outputs → Last policy sweep date. Scan for output files in the outputs folder that are dated after that date. If no date is recorded, scan all files and note: "First sweep — scanning all outputs."

If the outputs folder is empty or has no new files since the last sweep:

"No new outputs since [last sweep date]. Policy appears current with recent practice. Next scheduled sweep: [date]."

Update Last policy sweep in ~/.claude/plugins/config/claude-for-legal/privacy-legal/CLAUDE.md to today's date after completing the sweep.

Show full SKILL.md (811 more words)Show less
What to read in each output type

PIAs (Privacy Impact Assessments):

  • Extract: data categories processed, purposes, third parties / subprocessors involved, retention periods, user rights implications, any conditions placed on the processing
  • Flag: anything in that list not present in the current privacy policy commitments

DPA reviews (signed or approved):

  • Extract: subprocessors added, data locations agreed to, processing purposes covered, any obligations to data subjects created by the DPA terms
  • Flag: subprocessors not listed in the policy (if policy names them), new processing categories, new data locations, obligations inconsistent with policy

Triage results (PIA REQUIRED / PROCEED outcomes):

  • Extract: what was approved, any conditions imposed that imply a public commitment (e.g., "disclosure to affected parties required before launch")
  • Flag: approved practices not covered by policy, conditions that require policy language

DSAR responses:

  • Extract: any new data categories surfaced that weren't in previous DSAR responses, any systems added to the systems list
  • Flag: data categories collected but not stated in policy
Gap identification

For each flagged item, assess:

REQUIRED update — the policy makes a commitment that this output contradicts, or the processing is occurring and the policy has no coverage at all. Not updating creates a material misrepresentation.

Example: Policy says "we collect name, email, and payment information." A PIA approved collection of location data. Policy says nothing about location. That's a REQUIRED update — you're collecting data you haven't disclosed.

ADVISABLE update — the policy is silent but not in conflict. The processing is defensible without updating, but cleaner with it.

Example: Policy says "we may share data with service providers." A DPA was signed with a new analytics vendor. Policy doesn't name the vendor but doesn't exclude them either. Advisable to add to a named subprocessor list if one is maintained.

Sweep output format
markdown
[WORK-PRODUCT HEADER — per plugin config ## Outputs — differs by role; see `## Who's using this`]

# Privacy Policy Monitor — Sweep Report

**Date:** [date]
**Outputs scanned:** [N files] | **New since last sweep:** [N files]
**Gaps found:** [N] REQUIRED | [N] ADVISABLE

---

## REQUIRED updates

### [Gap 1 short name]

**Source:** [filename / output type that triggered this]
**What's happening:** [plain description of the new practice]
**Current policy:** [quote the relevant section — or "No coverage"]
**Gap:** [what's missing or inconsistent]

**Suggested language:**
> *Add to [section name]:*
> "[Drafted policy text — specific, consistent with house style of the actual policy]"

---

[repeat for each REQUIRED gap]

---

## ADVISABLE updates

### [Gap name]

**Source:** [filename]
**What's happening:** [description]
**Current policy:** [quote or "Silent"]
**Suggested language:**
> *Add to / update [section]:*
> "[Drafted text]"

---

## No action needed

[List outputs scanned where no gaps were found — confirms they were reviewed]

---

## Next steps

- [ ] Review REQUIRED updates — each needs a decision before the associated
  feature/processing goes live (or immediately if already live)
- [ ] Review ADVISABLE updates — lower urgency but worth addressing at next
  policy refresh
- [ ] Next scheduled sweep: [date]

Mode 2: Direct query

Parse the proposed practice

Extract from the user's description:

  • What data is being collected or processed?
  • What's the purpose?
  • Who else is involved (vendors, partners, third parties)?
  • Who are the data subjects?
  • Is there any automated decision-making?
  • Any new disclosure to data subjects required?

If the description is vague, ask one clarifying question before proceeding. Don't run a long intake — this mode should be fast.

Policy diff

Check the proposed practice against every relevant section of the current policy:

CheckCurrent policy saysProposed practiceVerdict
Data categories[what policy lists][new category if any]🟢 Covered / 🟡 Gap / 🔴 Conflict
Purposes[stated purposes][new purpose]
Third parties / subprocessors[stated parties][new party if any]
Retention[retention commitment][implied retention]
User rights[rights offered][any new rights implications]
Disclosure / notice[what policy says about telling users][what this practice requires]
Direct query output format
markdown
[WORK-PRODUCT HEADER — per plugin config ## Outputs — differs by role; see `## Who's using this`]

# Privacy Policy Check: [Proposed practice in one line]

**Bottom line:** [POLICY UPDATE REQUIRED / ADVISABLE / NO UPDATE NEEDED]

---

## What's covered

[List aspects of the proposed practice already addressed by the current policy —
brief, confirms they don't need to change]

## What's missing

### [Gap 1]

**Current policy:** [quote or "Silent"]
**What's needed:** [why this gap matters — legal, reputational, or consistency reason]

**Suggested language:**
> *Add to [section]:*
> "[Drafted text]"

### [Gap 2]
[same format]

## What conflicts

### [Conflict 1 — if any]

**Current policy says:** [quote]
**Proposed practice does:** [what conflicts]
**Resolution:** [which one needs to change and why — usually the practice adjusts
to match the policy, or the policy gets updated to a defensible new position]

---

## Timing

[If any gap is REQUIRED: "Policy update should happen before this goes live."
If ADVISABLE: "Can proceed; update at next policy refresh."]

Suggested language quality standards

Policy language should:

  • Match the voice and style of the existing policy (read the actual document, not just the config CLAUDE.md summary, before drafting)
  • Be specific enough to be meaningful but not so specific that routine changes break it ("service providers who assist us in operating our business" ages better than naming every vendor)
  • Not make commitments the team can't keep (e.g., don't draft "we will never share location data" if the architecture has that data flowing to an analytics vendor)
  • Flag where a broader policy position change might be needed, not just a sentence addition

When drafting, always say which section to add to. If the right section doesn't exist, say so and suggest creating it.

Schedule integration

Set up a recurring reminder in your own scheduler (calendar, task manager, or CI) to run /privacy-legal:policy-monitor weekly. Scheduled execution requires a scheduled-tasks integration, which is not bundled with this plugin.

Whenever the sweep runs, it updates ## Outputs → Last policy sweep in ~/.claude/plugins/config/claude-for-legal/privacy-legal/CLAUDE.md, so the next sweep only looks at new files.

Close with the next-steps decision tree

End with the next-steps decision tree per CLAUDE.md ## Outputs. Customize the options to what this skill just produced — the five default branches (draft the X, escalate, get more facts, watch and wait, something else) are a starting point, not a lock-in. The tree is the output; the lawyer picks.

If the sweep surfaced more than ~10 drift findings, or any time the user asks: offer the dashboard (see CLAUDE.md ## Outputs → Dashboard offer for data-heavy outputs). Shape the offer for this output — counts by surface (policy clause / PIA / DPA / triage), counts by severity, and a sortable grid of findings with source artifact and recommended remediation.

What this skill does not do

  • It doesn't update the policy itself — it drafts suggested language and flags decisions, but a human reviews and approves every change.
  • It doesn't catch regulatory changes — that's reg-gap-analysis. This skill monitors internal practice drift, not external legal changes.
  • It doesn't enforce that outputs are saved — if the team isn't saving PIAs to the configured folder, the sweep won't find them. The direct-query mode works without saved outputs.
  • It doesn't read email or Slack for informal decisions — only structured outputs saved to the configured folder.

© anthropics, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in privacy-legal/skills/policy-monitor of anthropics/claude-for-legal.

Open the folder on GitHubat commit 4a6c651

Used in 2 other repositories

We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 2 other GitHub owners. This page covers the copy in anthropics/claude-for-legal, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Policy Monitor next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Policy Monitor compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Policy Monitor this skillanthropics/claude-for-legal9.6k2 repos~4.5kAutomated safety check: PassApache-2.0
C15tc15t/c15t1.9k1 repos~1.6kAutomated safety check: PassApache-2.0
HIPAA Safe Harbor Coverage Auditmaziyarpanahi/openmed5.5k—~1.7kAutomated safety check: PassApache-2.0
Korean Privacy Termskimlawtech/korean-privacy-terms587—~2.9kAutomated safety check: PassApache-2.0
Gdpr ComplianceSushegaad/Claude-Skills-Governance-Risk-and-Compliance9461 repos~3.9kAutomated safety check: PassMIT
Hipaa ComplianceSushegaad/Claude-Skills-Governance-Risk-and-Compliance9461 repos~2.3kAutomated safety check: PassMIT

Similar skills

  • C15t

    c15t/c15t

    Work with c15t consent management docs, APIs, and integrations for Next.js, React, and JavaScript.

    1.9k GitHub starsUsed in 1 repo~1.6k tokens
    Legal & ComplianceAuto-check passed

  • HIPAA Safe Harbor Coverage Audit

    maziyarpanahi/openmed

    Checks OpenMed de-identified clinical text against the 18 HIPAA Safe Harbor identifier categories and reports gaps and residual re-identification risk.

    5.5k GitHub stars~1.7k tokensUpdated today
    Legal & ComplianceAuto-check passed

  • Korean Privacy Terms

    kimlawtech/korean-privacy-terms

    처리방침·이용약관 자동 생성 스킬 패키지 (v4.0). An agent skill from kimlawtech/korean-privacy-terms.

    587 GitHub stars~2.9k tokensUpdated 1 mo ago
    Legal & ComplianceAuto-check passed

  • Gdpr Compliance

    Sushegaad/Claude-Skills-Governance-Risk-and-Compliance

    Expert GDPR compliance assistant covering all four core workflows: (1) auditing code and systems for GDPR violations, (2) drafting GDPR-compliant documents such as privacy policies, Data Processing…

    946 GitHub starsUsed in 1 repo~3.9k tokens
    Legal & ComplianceAuto-check passed

  • Hipaa Compliance

    Sushegaad/Claude-Skills-Governance-Risk-and-Compliance

    Expert HIPAA compliance assistant for healthcare and software contexts.

    946 GitHub starsUsed in 1 repo~2.3k tokens
    Legal & ComplianceAuto-check passed

  • Pii Contract Analyze

    gregmos/PII-Shield

    Universal legal document processor with PII anonymization. An agent skill from gregmos/PII-Shield.

    150 GitHub stars~8.9k tokensUpdated 3 mo ago
    Legal & ComplianceAuto-check: notes

More from anthropics/claude-for-legal

All 147 skills in this repo

  • Legal Clinic Client Intake

    anthropics/claude-for-legal

    Official

    Structures a legal clinic client intake interview and produces a case summary with cross-area issue spotting, conflict flags and triage classification.

    9.6k GitHub starsUsed in 3 repos~3.2k tokens
    Auto-check passed

  • Supervisor Review Queue

    anthropics/claude-for-legal

    Official

    Holds student work in a queue for a legal clinic professor to approve, edit-then-approve or return before anything reaches clients or courts.

    9.6k GitHub starsUsed in 3 repos~1.1k tokens
    Auto-check passed

  • Tabular Document Review

    anthropics/claude-for-legal

    Official

    Builds a review grid with one row per document and one column per data point, each cell cited to a verbatim quote, built for M&A diligence and other batch reviews.

    9.6k GitHub starsUsed in 3 repos~4.3k tokens
    Auto-check passed

  • Product Launch Legal Review

    anthropics/claude-for-legal

    Official

    Runs a category-by-category legal review of a product launch from a PRD or tracker ticket, calibrated to your team's framework, and writes a review memo in house format.

    9.6k GitHub starsUsed in 2 repos~5k tokens
    Auto-check passed

  • Legal Skills Registry Browser

    anthropics/claude-for-legal

    Official

    Searches watched registries for community legal skills, shows matches with descriptions and offers the full SKILL.md before anything is installed.

    9.6k GitHub starsUsed in 2 repos~620 tokens
    Auto-check passed

  • Contract Renewal Tracker

    anthropics/claude-for-legal

    Official

    Shows which contracts renew soon and when notice must be sent by, working from a maintained renewal register, and warns about missed cancellation windows.

    9.6k GitHub starsUsed in 2 repos~3.1k tokens
    Auto-check passed

Categories

Questions about Policy Monitor

What does Policy Monitor do?

Keep the privacy policy current with practice. An agent skill from anthropics/claude-for-legal. Policy Monitor is an agent skill from anthropics/claude-for-legal, published by the product's own GitHub organization. Keep the privacy policy current with practice.

When should I use Policy Monitor?

Policy Monitor fits situations like: the user asks does our policy cover this; we want to start doing X — does the policy need updating; run the policy monitor; wants to find where the privacy policy no longer matches what the team actually does.

How do I install Policy Monitor in Claude Code?

Run `npx skills add anthropics/claude-for-legal --skill policy-monitor -a claude-code`. Or copy the skill folder (privacy-legal/skills/policy-monitor in anthropics/claude-for-legal) into .claude/skills/policy-monitor in your project. Claude Code loads it when a task matches its description.

How do I install Policy Monitor in Codex?

Run `npx skills add anthropics/claude-for-legal --skill policy-monitor -a codex`. Or copy the skill folder (privacy-legal/skills/policy-monitor in anthropics/claude-for-legal) into .agents/skills/policy-monitor in your project. Codex loads it when a task matches its description.

Can I use Policy Monitor in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add anthropics/claude-for-legal --skill policy-monitor -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/policy-monitor, .gemini/skills/policy-monitor, .github/skills/policy-monitor and .opencode/skills/policy-monitor in your project.

What does Policy Monitor need to run?

SKILL.md names no scripts, command-line tools or credentials: Policy Monitor is instructions for the agent only.

Does Policy Monitor access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Policy Monitor safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Policy Monitor use?

Policy Monitor is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Policy Monitor use?

About 4.5k tokens (SKILL.md is roughly 18k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Policy Monitor?

Skills that share tags, products or a category with Policy Monitor: C15t (c15t/c15t, 1.9k stars), HIPAA Safe Harbor Coverage Audit (maziyarpanahi/openmed, 5.5k stars), Korean Privacy Terms (kimlawtech/korean-privacy-terms, 587 stars) and Gdpr Compliance (Sushegaad/Claude-Skills-Governance-Risk-and-Compliance, 946 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Policy Monitor?

anthropics (a GitHub organization, an official publisher) maintains it in anthropics/claude-for-legal, which has 9,633 GitHub stars. The repository holds 147 skills in this directory. The repository was last updated on September 29, 2026.

Source: anthropics/claude-for-legal on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.