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 flanliulf/SpecLite --skill speclite-code-review-04-rules-extractorgit clone --depth 1 https://github.com/flanliulf/SpecLiteWrote 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/flanliulf/speclite/speclite-code-review-04-rules-extractor)<a href="https://agentmods.dev/skills/flanliulf/speclite/speclite-code-review-04-rules-extractor"><img src="https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-code-review-04-rules-extractor/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/flanliulf/speclite/speclite-code-review-04-rules-extractor"><img src="https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-code-review-04-rules-extractor.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 | $0.00075 | $0.01460 |
| Opus 5 | $0.00037 | $0.00730 |
| Sonnet 5 | $0.00015 | $0.00292 |
| Haiku 4.5 | $0.00007 | $0.00146 |
Grade A, and why
speclite-code-review-04-rules-extractor 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 7d 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
[技能说明] 从指定 Story 的历史代码审查、评估及修正记录中提炼共性问题和最佳实践,判断是否可以补充到项目全局文档中,避免同类问题在后续 Story 开发中重复出现。
[核心能力] - CR 历史分析:系统性阅读和分析 Story 的全部 CR 审查、评估及修正记录 - 四桶分类感知:识别审查结果中的「来源」和「分类」增强字段,按审查层维度(blind/edge/auditor)和四桶分类(decision_needed/patch/defer)进行交叉统计分析 - 共性问题识别:从多轮 CR 发现中识别重复出现的模式和共性问题 - 规则提炼:将共性问题转化为可操作的开发规约、指导原则或最佳实践 - 全局文档建议:评估提炼的规则是否适合补充到 project-context.md、architect.md 等全局文档 - 结构化输出:以清晰的结构输出分析结果和建议,供用户确认
[执行流程]
路径约定和文件名格式以 references/cr-config.md 为准。
Step 1:收集 CR 历史记录
- 接收用户指定的 Story 标识
- 读取 `references/cr-config.md` 获取路径约定
- 按配置中的 Story ID 规则提取 `{story-id}`
- 按配置中的代码审查目录格式确定路径
- 读取该目录下所有文件:
- 按配置中的审查总结文件名格式匹配 CR 代码审查结果
- 按配置中的审查评估文件名格式匹配 CR 评估结果(含 "## 修复执行记录" 章节)
- 生成数据:all-cr-records(全部 CR 历史记录)
Step 2:梳理各轮次模型信息
- 从每个 CR 文件的头部元信息中提取 `Model Used` 字段
- 构建模型使用时间线:哪一轮审查/评估/修复分别由哪个模型执行
- 生成数据:model-timeline(模型使用记录)
Step 3:分析 Findings 情况
- 系统性分析所有 CR 发现(Findings),分类统计:
- AC 验收标准审核摘要中的问题
- 测试充分性相关问题
- 质量门禁相关问题
- 代码逻辑和设计问题
- 安全性和性能问题
- 若发现包含「来源」字段,按审查层维度统计各层的发现分布和命中率
- 若发现包含「分类」字段,按四桶分类维度统计各分类的占比和修复率
- 标记哪些问题在多轮 CR 中重复出现
- 标记哪些问题的修复引入了新问题
- 生成数据:findings-analysis(发现分析报告)
Step 4:提炼共性规则
- 从分析结果中提炼出 Story 开发过程中容易重复出现的共性问题
- 将共性问题转化为以下形式:
- **规避指南**:明确告诉开发者应避免什么
- **指导原则**:描述推荐的做法和原因
- **最佳实践**:提供可直接参照的代码模式或流程
- **豁免说明**:记录合理的例外情况和豁免理由
- 生成数据:extracted-rules(提炼的规则列表)
Step 5:评估全局文档更新建议
- 扫描项目中的全局文档(包括但不限于):
- `project-context.md`
- `architect.md` 或 `architect/` 目录下的文档
- `CLAUDE.md` 等开发指南文档
- 对每条提炼的规则,评估:
- 是否具有跨 Story 的普适性?
- 适合补充到哪个全局文档?
- 建议放在文档的哪个章节?
- 生成数据:update-suggestions(文档更新建议列表)
Step 6:输出总结供用户确认
- 将分析结果、提炼的规则和文档更新建议整理为结构化总结
- 包含以下部分:
- 模型使用时间线(各轮次使用的模型及其角色)
- CR Findings 概况统计(含审查层分布和四桶分类占比,如有)
- 识别的共性问题(含出现频次)
- 提炼的规则/指南/最佳实践
- 全局文档更新建议(含具体文档和章节)
- 向用户展示总结,等待确认后再执行实际的文档更新
- 完成后返回:"✅ CR 历史分析和规则提炼完成,请确认是否需要更新全局文档"
[注意事项]
- 本 Skill 只输出分析结果和建议,不自动修改全局文档,需等待用户确认
- 路径约定和文件名格式以 references/cr-config.md 为准,不硬编码
- 始终使用中文输出
- 提炼的规则要具体可操作,避免过于抽象的描述(如 "注意代码质量")
- 如果某条规则只在特定技术栈或场景下适用,需要明确标注适用范围
- 如果 CR 历史记录较少(只有 1 轮),可能不足以提炼共性规则,需如实告知用户
- 避免将仅适用于当前 Story 的特殊情况泛化为全局规则
- 审查结果中的「来源」和「分类」字段为可选增强信息,若存在则利用其进行交叉统计分析,若不存在则按原有逻辑分析
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.
- 7d ago First seen · 93 lines · 75 tokens per session scan A 81dc0b99820d
speclite-code-review-04-rules-extractor is a skill published in the GitHub repository flanliulf/SpecLite (4 stars, last pushed 2mo ago), licensed MIT. It adds 75 tokens to every session and 1,460 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 skills, from other repositories
Security Audit Checklist
A PASS/FAIL/N/A checklist covering injection, authorization, secrets handling, dependency risk, and input validation for reviewing a diff or codebase.
PR Standards
Pull request description, review depth, and merge standards so every PR carries enough context to review and merge safely.
eng
Platform-agnostic engineering agent with three modes: --plan (propose file changes for human approval AND write the per-feature todo tickets in the same pass), --build (write code from the todo tickets — the single and final build spec), --review (one adversarial whole-change review of the working diff, run by a…
Security Checklist
A structured PASS / FAIL / N/A checklist covering common risk categories for reviewing a diff before merge.
Agent Instruction Drift Check
Procedure for comparing an agent-facing instruction doc (AGENTS.md/CLAUDE.md-style) against the actual current code and configuration to find and flag mismatches.
Code Standards
Naming, structure, and consistency conventions for keeping a codebase readable and predictable as it grows.