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 auto-updatergit 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/auto-updater)<a href="https://agentmods.dev/skills/zhou210712/claude-for-legal-zh/auto-updater"><img src="https://agentmods.dev/badge/skills/zhou210712/claude-for-legal-zh/auto-updater/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/auto-updater"><img src="https://agentmods.dev/badge/skills/zhou210712/claude-for-legal-zh/auto-updater.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 | $0.00050 | $0.01439 |
| Opus 5 | $0.00025 | $0.00720 |
| Sonnet 5 | $0.00010 | $0.00288 |
| Haiku 4.5 | $0.00005 | $0.00144 |
Grade A, and why
auto-updater 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/auto-updater
- 加载
~/.claude/plugins/config/claude-for-legal/legal-builder-hub/CLAUDE.md→ 已安装技能 + 自动更新偏好。 - 使用以下工作流。
- 检查每个已安装技能的源是否有更新版本。
- 按偏好:应用 / 通知 / 展示差异。
目的
社区技能会改进。本技能注意到改进时机,展示变更内容,仅在获得明确批准后应用更新。
信任姿态
已安装技能是在你特权法律环境中运行的代码。上游仓库可能被攻破、转让给新所有者、或以你不希望的方式改变行为。本技能的设计确保在没有你阅读差异并批准的情况下,绝无任何更新被应用。 这不是偏好——这是设计。
加载上下文
~/.claude/plugins/config/claude-for-legal/legal-builder-hub/CLAUDE.md → 已安装技能(附版本/提交 SHA)、更新偏好(通知 / 手动)。
工作流
第1步:检查每个已安装技能
对已安装列表中的每个技能:
- 从源注册表获取当前提交 SHA(精确提交,非标签或分支头——标签可变且可被发布者追溯改写;仅提交 SHA 不可变)
- 与安装时固定的 SHA 比较
- 如不同:有可用更新
第2步:差异与信任审查
对于每个更新,展示完整差异:
# [技能名称] — [已安装 SHA] → [最新 SHA]
## SKILL.md 变更
[统一差异]
## hooks/hooks.json 变更
[统一差异 — 标记:hooks 可执行任意代码]
## .mcp.json 变更
[统一差异 — 标记:MCP 服务器以你的凭据运行]
## 其他文件
[附差异的新增/删除/修改文件列表]
然后运行信任检查:
hooks/hooks.json是否变更? Hooks 可执行任意 shell 命令。显著展示差异并请用户确认他们理解新 hooks 的功能。.mcp.json是否变更? 新增或变更的 MCP 服务器可访问你的环境。同样处理。allowed-tools或toolsfrontmatter 是否扩展? 新增工具访问是权限提升。- SKILL.md 中是否有新增的网络调用、技能目录外的文件写入或命令执行? 标记它们。
- 技能的
description或声明的目的是否变化? 声称"审查保密协议"现在声称"发送合同"的技能已改变其用途。
第2.5步:重新扫描新版本(GlassWorm 门控)
在应用更新前,对新版本重新运行完整的 skills-qa 扫描。一个在 v1.0 干净的技能可能在 v1.1 携带有害内容(GlassWorm 模式:受信任的发布者、已建立的技能、携带有害代码的小版本号升级)。安装时的信任不转移到更新。
规则:
- 发现回归时不应更新。 如果新版本产生了旧版本没有的发现——在任何
skills-qa第1.5步类别中——默认拒绝更新并解释原因。 - 安全面差异无论评估结果如何均需人工批准。 任何涉及
hooks/hooks.json、.mcp.json、allowed-tools/toolsfrontmatter、新增Bash/WebFetch/WebSearch访问、新增外部 URL、技能目录外的新增文件写入路径或descriptionfrontmatter 的差异均需强制人工批准提示,不能被干净的 LLM 扫描绕过。 - 只读扫描上下文。 扫描读取攻击者控制的文本(新 SKILL.md)。在可用时在只读子代理中运行。安装代理接收子代理的报告;仅在人工批准后才获得写权限。
- 拒绝扫描现在失败的更新。 如果新版本命中
REFUSE层级模式,不提供"仍然应用"选项。
第2.6步:新鲜度触发的重新核实
不仅检查新提交。还检查已安装技能是否已过新鲜度窗口。
对于每个已安装技能,从安装日志读取已验证的 last_verified、freshness_window 和 freshness_category 标记。
如果活跃窗口已过且无更新的提交: 提供选项:(a) 自行检查来源,(b) 标记给注册表维护者,(c) 禁用该技能直至重新核实。
如果活跃窗口已过且有更新的提交: 始终重新核实,不静默应用。
第3步:按偏好处理
通知(默认): 展示完整差异和信任检查。"有可用更新。审查以上差异。应用?[y/n]"
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 · 110 lines · 50 tokens per session scan A 0c0bccb4dd81
auto-updater 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 50 tokens to every session and 1,439 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
specification-writing
A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.
regulatory-research-fallback
Fallback workflow for regulatory research when web extraction tools fail on government PDFs.
x-scorecard
OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.
memstack-business-gdpr
Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…
nda-review
Use when the user uploads or pastes a non-disclosure agreement and asks for review, redline, risk assessment, or a recommendation on whether to sign. Identifies missing standard protections, one-sided or unusual provisions, and operational issues; produces a structured report with severity ratings and citations to…