Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add skymanbp/cc-enforcer/plugin install cc-enforcerWrote 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/skymanbp/cc-enforcer/repo-refresh)<a href="https://agentmods.dev/skills/skymanbp/cc-enforcer/repo-refresh"><img src="https://agentmods.dev/badge/skills/skymanbp/cc-enforcer/repo-refresh/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/skymanbp/cc-enforcer/repo-refresh"><img src="https://agentmods.dev/badge/skills/skymanbp/cc-enforcer/repo-refresh.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 | $0.00160 | $0.02161 |
| Opus 5 | $0.00080 | $0.01081 |
| Sonnet 5 | $0.00032 | $0.00432 |
| Haiku 4.5 | $0.00016 | $0.00216 |
Grade A, and why
repo-refresh 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 8d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
repo-refresh — 全库更新扫描
你（主代理）已被本 skill 接管。这是
rules/12-repo-wide-sync.md主动半区的强制执行入口：对整个仓库做一次"陈旧 / 过时 / 冗余 / 错误 / 漂移" 五类缺陷的系统式清扫。规则 01（验证）、04（完整阅读）、05（引用）、06（收敛） 全程适用：每条 finding 必须有file:line证据；每次修复必须走收敛验证。
五类缺陷（扫描目标的定义）
| 类别 | 定义 | 典型证据形态 |
|---|---|---|
| 陈旧 (stale) | 引用了已不存在的文件 / 符号 / 路径 / 命令；早已完成或废弃却仍挂着的 TODO / FIXME；针对已移除工作流的操作说明 | 引用处 file:line + 被引对象不存在的证明（ls / Grep 0 命中） |
| 过时 (outdated) | 在某个历史版本为真、在 HEAD 已为假的数量、版本号、日期、行为描述、结构树 | 文档陈述 file:line + 当前权威源的相反证据 |
| 冗余 (redundant) | 同一事实在多处重复且无单一源标注；死代码 / 无引用的导出；被新文档取代却未删除的旧文档 | 各重复处 file:line + 引用图（谁还在用） |
| 错误 (wrong) | 与当前代码直接矛盾的断言：错误默认值、错误 CLI 标志、错误 file:line 引用、错误示例输出 |
断言处 + 权威源两个 file:line 对照 |
| 漂移 (drift) | 本应互为镜像的成对物已分叉：文档 ↔ 代码、英文骨架 ↔ 翻译、配置 ↔ 消费方、注释 ↔ 实现 | 成对两侧 file:line + diff 要点 |
强制流程（按顺序，不允许跳步）
Step 1 · 建立仓库清单与权威源
- 枚举全部待扫文件（
git ls-files或等价；排除 lockfile / 生成物 / vendored）。 - 确定权威源清单：版本号以哪个文件为准？行为以哪层代码为准？结构树以磁盘为准。 之后所有"过时/错误"判定都以权威源为基准，不做两两互比（一对可以一起漂—— rule 06 验证 2b）。
- 向用户报告扫描范围（文件数、目录划分）；范围有裁剪必须显式说明裁掉了什么。
Step 2 · 逐类扫描（五类都要过，不允许只挑好找的）
对每一类：先用 Grep/Glob 定位候选，再 Read 上下文确认（规则 04： 关键词检索只定位、不理解）。最低覆盖动作：
- 陈旧：提取文档/注释中的路径、命令、符号引用 → 逐个对磁盘/代码核对存在性； 枚举所有 TODO / FIXME / "暂时" → 核对是否已完成或已无意义。
- 过时：提取所有数量词（"N 个测试"、"X 条规则"）、版本号、日期、结构树 → 与权威源逐个对照。
- 冗余：对关键事实做全库 Grep，列出重复陈述点 → 判定哪个是源、其余应删或改为 指向源的交叉引用；对代码做无引用符号检查。
- 错误：抽查文档中的行为断言（默认值 / 标志 / 示例）→ 用 Read/运行验证；
文档里的
file:line引用逐个核对仍然指向所述内容。 - 漂移：枚举已知镜像对（本仓库类比：
rules/↔rules/zh/、doc ↔ hook 实现、 sync-gate 组的 when ↔ require）→ 逐对比对结构与语义。
Step 3 · Findings 表（先报告，后动手）
汇总为一张表：类别 | file:line | 现状 | 权威源证据 | 提议处置（fix / delete / 保留并说明）。
删除类处置（删文件、删整段文档）先呈报用户确认再执行；就地纠错类（改数字、
改路径、补引用）可直接修。没有证据的行不允许进表。
Step 4 · 系统式修复
- 按 rule 09：同类问题一次性全修，不滚动打小补丁；批量替换走 rule 09 六步 （勘察 → 白名单 → 拒绝报告 → 算术自洽）。
- 按 rule 12 被动半区：每个修复自身也要连带更新（改了数量 → 所有陈述处一起改）。
Step 5 · 收敛验证（rule 06）
- 重跑 Step 2 中命中的那几条扫描 → 确认 finding 消失；
- 跑仓库既有门禁（测试 / lint / i18n 检查 / 版本同步门）确认连带不破；
- 自答 4 题；比对集合不比总数（验证 2b）。
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.
- 8d ago First seen · 103 lines · 160 tokens per session scan A 7a34fc95ddc6
repo-refresh is a skill published in the GitHub repository skymanbp/cc-enforcer (5 stars, last pushed 5d ago), licensed MIT. It adds 160 tokens to every session and 2,161 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
audit
This skill should be used when the user asks to "audit spec coverage", "find uncovered modules", "scan for missing specs", "check wyx coverage", "get spec TODO list", "wyx audit", "wyx", or wants a prioritized list of wyx skill commands for uncovered modules. Scans for coverage gaps, pipeline/sync candidates, and…
recipe-front-review
Reviews completed frontend implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved React corrections.
new-skill
Scaffold a new brooks-lint analysis skill so it passes npm run validate and npm run evals on the first try — generates skills/{name}/SKILL.md (with the mandatory "Do NOT trigger for:" clause and a Process section citing guide step ranges) plus skills/{name}/{name}-guide.md (sequentially numbered steps), then appends…
release
Cut a brooks-lint release: set the version in package.json, propagate it across all four plugin manifests and every version-bearing text file (README badges, docs site metadata), write the CHANGELOG entry, validate, then commit, push, tag, and publish the GitHub release. Triggers when the maintainer asks to "release"…
brooks-audit
Architecture audit that maps module dependencies, checks layering integrity, and flags structural decay across a codebase, drawing on twelve classic engineering books. Triggers when: user asks to audit architecture, review folder/module structure, check for circular imports, understand how the codebase is organized…
brooks-review
PR code review that surfaces decay risks, design smells, and maintainability issues with concrete Symptom → Source → Consequence → Remedy findings, drawing on twelve classic engineering books. Triggers when: user asks to review code, check a PR, shares a diff or pastes code asking "does this look right?" / "any issues…