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 Buildwise-Studios/claude-for-hk-law --skill policy-monitorgit clone --depth 1 https://github.com/Buildwise-Studios/claude-for-hk-lawWrote 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/buildwise-studios/claude-for-hk-law/policy-monitor)<a href="https://agentmods.dev/skills/buildwise-studios/claude-for-hk-law/policy-monitor"><img src="https://agentmods.dev/badge/skills/buildwise-studios/claude-for-hk-law/policy-monitor/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/buildwise-studios/claude-for-hk-law/policy-monitor"><img src="https://agentmods.dev/badge/skills/buildwise-studios/claude-for-hk-law/policy-monitor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00082 | $0.03400 |
| Opus 5 | $0.00041 | $0.01700 |
| Sonnet 5 | $0.00016 | $0.00680 |
| Haiku 4.5 | $0.00008 | $0.00340 |
Grade A, and why
policy-monitor 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 12d 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.
This is a copy
86% identical to policy-monitor — 20 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 355 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/policy-monitor
Sweep mode (no argument or --sweep):
- Read
~/.claude/plugins/config/claude-for-hk-law/ai-governance-legal/CLAUDE.md→ outputs folder path, AI policy document, last sweep date. - Use the framework below. Scan outputs folder for files since last sweep.
- For each output: extract approved practices → diff against current policy commitments and use case registry.
- Classify gaps: REQUIRED (policy misrepresents current practice) vs ADVISABLE (policy silent).
- For each gap: quote current policy, describe gap, draft suggested language.
- Flag any use cases in outputs not yet added to the
~/.claude/plugins/config/claude-for-hk-law/ai-governance-legal/CLAUDE.mdregistry. - Present results to the human. Only after acknowledgment, update
Last policy sweepandgaps_foundin~/.claude/plugins/config/claude-for-hk-law/ai-governance-legal/CLAUDE.md.
Direct query mode (with description argument):
- Read
~/.claude/plugins/config/claude-for-hk-law/ai-governance-legal/CLAUDE.md→ current policy commitments, use case registry, actual policy document. - Parse proposed practice. Diff against policy: use case coverage, automation level, affected parties, disclosure, vendor data use, oversight.
- Output: covered / missing / conflicting + suggested language for each gap + registry entry if needed + timing recommendation.
Recurring runs:
Set up a recurring reminder in your own scheduler to run /ai-governance-legal:policy-monitor weekly. Scheduled execution requires a scheduled-tasks integration, which is not bundled with this plugin.
/ai-governance-legal:policy-monitor
/ai-governance-legal:policy-monitor "We want to use AI to automatically flag expense reports for review"
Purpose
AI policies drift from practice faster than almost any other policy document — the field moves quickly, use cases multiply, and each approved AIA or triage result represents a new commitment the policy may not have caught up with. An AIA approves a new AI use case with a human-oversight condition. A vendor AI agreement permits data processing the policy doesn't mention. A triage result marks a new category of deployment as conditional with a disclosure requirement. The policy sits there unchanged.
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.
- 12d ago First seen · 355 lines · 82 tokens per session scan A 9f39502561d4
policy-monitor is a skill published in the GitHub repository Buildwise-Studios/claude-for-hk-law (5 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 82 tokens to every session and 3,400 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to policy-monitor, differing in 20 lines, and is treated as a copy.
Other skills, from other repositories
c2pa-metadata
Embed a C2PA provenance manifest into an AI-generated marketing asset (PNG, JPG, WebP, GIF, TIFF, MP4, MOV, WebM, MP3, WAV, PDF) via scripts/embed-c2pa.py — produces a signed copy of the file carrying IPTC digital-source-type AI claims, an optional c2pa.ai-disclosure assertion for EU AI Act Article 50 (applicable 2…
employment-compliance
Covers the employment rules that carry real penalties — exempt and non-exempt classification, overtime and hours, employee versus contractor status, work authorization and recordkeeping, accommodation requests, and the notices and retention obligations that go with them. Use this to classify a role, review a…
privacy-jp
A Japanese-language document generator for services built with Next.js. It creates privacy policies, terms of service, consent dialogs, and cookie banners while considering Japan's personal-information and consumer-protection laws.
revenue-recognition
Determines when and how revenue is recognized — performance obligations, contract terms that change the answer, and the deal structures that create accounting problems. Use this to work out how a contract should be recognized, review a non-standard deal before it is signed, understand deferred revenue, or spot terms…
contract-review
Reviews and negotiates commercial agreements — MSAs, SOWs, order forms, NDAs, vendor and data-processing agreements — identifying material risk, proposing positions, and recommending a path rather than listing issues. Use this to review a contract before signature, prepare a negotiation position, build fallback…
privacy-and-data-protection
Assesses and improves how personal data is collected, used, shared, and retained — data mapping, lawful basis, consent, processor agreements, subject rights, and breach obligations. Use this before launching anything that handles personal data, when adding a vendor that will process it, when a data subject request…