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 gap-surfacergit 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/gap-surfacer)<a href="https://agentmods.dev/skills/zhou210712/claude-for-legal-zh/gap-surfacer"><img src="https://agentmods.dev/badge/skills/zhou210712/claude-for-legal-zh/gap-surfacer/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/gap-surfacer"><img src="https://agentmods.dev/badge/skills/zhou210712/claude-for-legal-zh/gap-surfacer.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 | $0.00106 | $0.01653 |
| Opus 5 | $0.00053 | $0.00826 |
| Sonnet 5 | $0.00021 | $0.00331 |
| Haiku 4.5 | $0.00011 | $0.00165 |
Grade A, and why
gap-surfacer 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.
How it starts
The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
差距呈现
负责人通知：默认开启。如需选择某个负责人不接收通知，将
owner_contact留空。
逐次发送确认——无例外
在发送任何通知消息（分配通知、逾期提醒、批量通知、状态报告）之前：
- 向用户展示你即将发送给谁、发送什么内容。
- 等待明确的同意。
- 绝不要不经确认就发送。不因是定时任务而跳过。不因是批量而跳过。不因昨天发送过而跳过。
未经确认的自动发送是本插件中最不可逆的操作——发送了插件自身页脚声明可能出错的内容，给无法检查的人。这种组合不能跳过审阅。
目的
差距被发现后就忘了。此技能跟踪它们直到关闭，并通知负责关闭它们的人。
跟踪文件
位于 ~/.claude/plugins/config/claude-for-legal/regulatory-legal/gap-tracker.yaml：
gaps:
- id: GAP-001
requirement: "[法规要求的内容]"
regulation: "[名称 + 引用]"
policy_affected: "[名称或'需要制定新政策']"
gap_type: "partial" # none | partial | full | new-policy | watch | comment-decision
owner: "[政策索引中的姓名]"
owner_contact: "[联系方式，如已知]"
opened: 2026-03-01
due: 2026-06-01 # 法规生效日期、内部截止日期或意见征集截止日期
status_verified: true # 如果上游政策差异分析无法确认法规有效，则为false；未验证的事项永不会进入🔴逾期分类
status: "open" # open | in-progress | closed | risk-accepted
notified: false # 分配通知发送后设为true
resolution: "" # 关闭时填写
绝不要将差距分类为"逾期"——如果法规未经验证。 🔴逾期分类意味着"我们错过了一个具有约束力的截止日期"。如果法规状态未经验证（政策差异分析设置了 status_verified: false，或法规>12个月/已超过适用日期且未确认时效性），截止日期可能不具有约束力。使用🟡"需要审查"并注明。
gap_type 语义：
| 值 | 含义 | 典型提醒频率 |
|---|---|---|
none |
政策已涵盖此要求。仅为审计追踪记录。 | 无自动提醒。 |
partial |
政策涵盖该主题但未完全覆盖新要求。需要修订。 | 到期前30天。 |
full |
政策与新要求矛盾或未提及。需要重写或添加新章节。 | 到期前30天。 |
new-policy |
现有政策中无此项内容。需要起草政策。 | 到期前30天。 |
watch |
前瞻性事项——预征求意见、调研通知、尚未最终确定的征求意见稿。当前没有合规义务；政策工作等待正式法规出台。due: 是重访日期，不是合规截止日期。 |
无自动提醒；在征求意见稿发布时或重访日期重新评估。 |
comment-decision |
预规则意见征集决策待定——团队正在决定是否提交反馈意见。due: 是意见征集截止日期。 |
截止日期前21天（比合规差距更紧凑）。 |
模式
模式1：从政策差异分析中获取
当政策差异分析发现差距时，追加到 gap-tracker.yaml。去重——相同要求 + 相同政策 = 相同差距，不重复计算。
获取后，通知负责人：
如果企业通讯工具可用且 owner_contact 已设置：向差距负责人发送通知——但仅在完成逐次发送确认之后。预览消息给用户，等待明确的同意，然后发送。发送后将 notified: true 设置在跟踪条目中。
模式2：状态报告
[工作成果头 — 按照插件配置 ## 输出]
## 开放差距 — [日期]
### 要点
[N个差距需要在[日期]前采取行动 — 前3项：X、Y、Z]
### 🔴 逾期
| ID | 要求 | 政策 | 负责人 | 截止日期 | 逾期天数 |
|----|------|------|--------|----------|---------|
| | | | | | |
### 🟠 30天内到期
[同上]
### 🟡 开放
[同上]
### 👀 观察事项（前瞻性——预法规）
[预法规跟踪——`watch` 和 `comment-decision` 条目。这些不是合规差距。单独呈现。]
### 进行中
[同上]
### 最近关闭
[最近5项，附解决方案]
---
**最早开放的差距：** [ID]，[N]天
**按负责人分组的差距：** [分布]
**负责人通知已发送：** [N] / [N个总差距]
---
**依赖前核实引注。** 此跟踪文件中的法规引注由AI在上游生成（reg-feed-watcher 和 policy-diff），未经对照一手来源核实。在关闭、接受风险或引用到任何合规声明、董事会报告或监管机构回复之前，通过法律研究工具确认。
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 147 lines · 106 tokens per session scan A 30932d6750b9
gap-surfacer 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 106 tokens to every session and 1,653 once invoked, about $0.0005 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.