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 zhou210712/claude-for-legal-ZH --skill commentsgit 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/skills/zhou210712/claude-for-legal-zh/comments)<a href="https://agentmods.dev/skills/zhou210712/claude-for-legal-zh/comments"><img src="https://agentmods.dev/badge/skills/zhou210712/claude-for-legal-zh/comments/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/zhou210712/claude-for-legal-zh/comments"><img src="https://agentmods.dev/badge/skills/zhou210712/claude-for-legal-zh/comments.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 | $0.00065 | $0.00724 |
| Opus 5 | $0.00032 | $0.00362 |
| Sonnet 5 | $0.00013 | $0.00145 |
| Haiku 4.5 | $0.00006 | $0.00072 |
Grade A, and why
comments 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
/comments
目的
征求意见稿有截止日期。是否提交反馈意见是律师的决定——但截止日期在未被记录决策的情况下悄然消失才是风险。此技能呈现开放的征求意见期并记录决策。
加载上下文
~/.claude/plugins/config/claude-for-legal/regulatory-legal/comment-tracker.yaml → 所有已跟踪的征求意见稿及其状态。
~/.claude/plugins/config/claude-for-legal/regulatory-legal/CLAUDE.md → 默认意见征集决策负责人。
默认视图——开放的征求意见期
## 意见征集跟踪器 — [日期]
### ⏰ 14天内截止
| ID | 法规 | 截止日期 | 剩余天数 | 决策 | 负责人 |
|----|------|----------|----------|------|--------|
| CMT-001 | [名称] | [日期] | [N] | 待决定 | [负责人] |
### 🟡 开放（>14天）
[同上表]
### 最近已决定
| ID | 法规 | 决策 | 理由 |
|----|------|------|------|
| CMT-002 | [名称] | 不提交 | [理由] |
---
**总开放数：** [N] **30天内截止且待决定：** [N]
记录决策
/regulatory-legal:comments --decide CMT-001
决策：[提交 / 不提交 / 放弃]
理由："[简要——如'该法规不适用于我们的业务模式'或'就第3条提交意见']"
更新跟踪器。如果决策为"提交"：提示设置提交截止日期提醒（征求意见截止日期前至少5个工作日供内部审阅）。
通知
首次检测到征求意见稿时（由 reg-feed-watcher 填充）：向意见征集决策负责人发送通知（如企业通讯工具已配置且 owner_contact 已设置）。
截止日期前14天提醒（如决策仍为"待决定"）。 截止日期前3天提醒（如仍待决定）——升级紧急度。
comment-decision的gap_type语义、逐次发送确认规则和 comment-tracker.yaml 的 schema 位于 gap-surfacer 参考技能中——在实质工作前加载。
本技能不做的事
- 不起草意见书。那是独立的律师任务。
- 不做出提交决策。它跟踪决策；律师做出决策。
- 不监测征集后的活动。一旦决策已记录，此跟踪器的工作就完成了——通过
/regulatory-legal:reg-feed-watcher跟踪规则的后续进展。
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 · 70 lines · 65 tokens per session scan A e2ba723ceebe
comments is a skill published in the GitHub repository zhou210712/claude-for-legal-ZH (212 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 65 tokens to every session and 724 once invoked, about $0.0003 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 skills, from other repositories
vendor-review
Evaluate a vendor — cost analysis, risk assessment, and recommendation. Use when reviewing a new vendor proposal, deciding whether to renew or replace a contract, comparing two vendors side-by-side, or building a TCO breakdown and negotiation points before procurement sign-off.
entity-compliance
Entity compliance tracker — initialize, report upcoming deadlines, update status, run health audit, export to CSV. Maintains a compliance-tracker.yaml built from the entity table, calculates filing deadlines by entity and jurisdiction, and surfaces what's due in the next 30/60/90 days. Use when user says "entity…
integration-management
Post-closing M&A integration tracker — phased workplan, consent tracking, contract assignment at scale, weekly status reports. Initializes from whatever deal artifacts are available (purchase agreement, deal summary, closing checklist) and connects to deal-context.md and closing-checklist.yaml from the M&A cold-start.…
matter-workspace
Manage matter workspaces — new, list, switch, close, or detach (practice-level). File-management logic for keeping one client or engagement's context separate from every other. Use when working across multiple clients or matters, when the user says "new matter", "switch matter", "list matters", "close matter", or when…
patent-docket
A workflow coordinator for patent case files, from an inventor's technical disclosure to patent application documents. A patent docket is the tracked record of a patent matter, including its stage, questions, drafts, and handoffs.
performance-management
Runs performance systems that change behavior — expectations, feedback, review cycles, calibration, and handling underperformance. Use this to design or fix a review process, run calibration, write or coach on feedback, address sustained underperformance, or work out why reviews consume weeks and change nothing.