speclite-code-review-04-rules-extractor

speclite-code-review-04-rules-extractor is a skill for Claude Code from flanliulf/SpecLite. It costs 75 tokens per session (1,460 once invoked), scanned A, original, MIT.

A tool that studies past code reviews, their assessments, and their fixes to extract reusable development rules.

In plain words
What is it for?
Use it to analyze repeated findings, compare review rounds, and suggest updates to project-wide engineering documents.
Why use it?
It helps teams identify recurring problems and turn review history into guidance for future work.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md.

Good fit Use it to analyze repeated findings, compare review rounds, and suggest updates to project-wide engineering documents.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/flanliulf/speclite/speclite-code-review-04-rules-extractor
Install

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.

Any agent
npx skills add flanliulf/SpecLite --skill speclite-code-review-04-rules-extractor
Clone the repo
git clone --depth 1 https://github.com/flanliulf/SpecLite

Made for: Claude Code.

Wrote 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.

agentmods badge for speclite-code-review-04-rules-extractor

README.md
[![agentmods](https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-code-review-04-rules-extractor/github.svg)](https://agentmods.dev/skills/flanliulf/speclite/speclite-code-review-04-rules-extractor)
Your own site
<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.

agentmods 80×15 button for speclite-code-review-04-rules-extractor

Your own site · 80×15
<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>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,460 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 7d ago against content hash 81dc0b99820d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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.

assets/source/speclite/sdlc-skills/4-implementation/speclite-code-review-04-rules-extractor/SKILL.md · 93 lines

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

Files

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.

Changes

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.

  1. 7d ago First seen · 93 lines · 75 tokens per session scan A 81dc0b99820d

Subscribe to this mod's changes

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.