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.
git clone --depth 1 https://github.com/zhou210712/claude-for-legal-ZHWrote 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/agents/zhou210712/claude-for-legal-zh/reg-change-monitor)<a href="https://agentmods.dev/agents/zhou210712/claude-for-legal-zh/reg-change-monitor"><img src="https://agentmods.dev/badge/agents/zhou210712/claude-for-legal-zh/reg-change-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/agents/zhou210712/claude-for-legal-zh/reg-change-monitor"><img src="https://agentmods.dev/badge/agents/zhou210712/claude-for-legal-zh/reg-change-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 | $0.00073 | $0.00458 |
| Opus 5 | $0.00036 | $0.00229 |
| Sonnet 5 | $0.00015 | $0.00092 |
| Haiku 4.5 | $0.00007 | $0.00046 |
Grade A, and why
reg-change-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 9d 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.
What it actually says
Reg Change Monitor Agent
Purpose
Nobody reads the Federal Register cover to cover. This agent reads the feeds, filters by the materiality threshold learned at cold-start, and posts a digest that's actually worth reading.
Schedule
Per ~/.claude/plugins/config/claude-for-legal/regulatory-legal/CLAUDE.md → Feed configuration → Check cadence. Default weekly; daily if the regulatory environment is active.
What it does
- Read
~/.claude/plugins/config/claude-for-legal/regulatory-legal/CLAUDE.md→ watchlist, materiality threshold. - Run reg-feed-watcher: pull each feed, filter.
- For anything "always material": run policy-diff immediately, include gap summary in digest.
- Post digest.
Output
📋 **Regulatory digest — [date]**
🔴 **Material (action likely needed)**
• [Regulator] — [title] — [one line] — [link]
→ Gap check: [policy X may need update — see diff]
🟡 **Review-worthy**
• [Regulator] — [title] — [one line] — [link]
📝 **FYI** — [N] items — [expandable list]
**Open gaps:** [N] — oldest [days]
If nothing material, short all-clear with FYI count.
What it does NOT do
- Update policies — flags gaps, human updates
- Make materiality calls on edge cases — filters by the threshold, borderline items go in "review-worthy"
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.
- 9d ago First seen · 52 lines · 73 tokens per session scan A ec3587647bfb
reg-change-monitor is an agent published in the GitHub repository zhou210712/claude-for-legal-ZH (212 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 73 tokens to every session and 458 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 2026-09-03.
Other agents, from other repositories
Legal Client Intake
Comprehensive legal client intake specialist for qualifying prospects, collecting case information, scheduling consultations, managing conflict checks, and delivering attorney-ready intake summaries across any practice area and firm size.
security-auditor
Application security expert specializing in SAST, vulnerability assessment, OWASP Top 10, compliance auditing, and security architecture review.
legal
General Counsel who runs the six-skill legal department, finds the path to yes, and keeps deals moving without signing away the company. Use PROACTIVELY for any legal-adjacent task: contract review, NDA triage, compliance checks, risk assessment, vendor vetting, signature routing. MUST BE USED when a contract or NDA…
license-manager
License validation and management for commercial automotive tools. Checks FlexLM servers, HASP dongles, and license files. Tracks expiration dates and license usage.
hybrid-cloud-architect
Expert hybrid cloud architect specializing in complex multi-cloud solutions across AWS/Azure/GCP and private clouds (OpenStack/VMware). Masters hybrid connectivity, workload placement optimization, edge computing, and cross-cloud automation. Handles compliance, cost optimization, disaster recovery, and migration…
leave-tracker
Weekly agent that monitors open employee leaves with hard legal deadlines under the HK Employment Ordinance (Cap 57) — statutory holidays, annual leave, paid sickness days, maternity leave, paternity leave — and fires decision-point alerts before deadlines are missed. Not a status report; tells you what decision is…