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 okwinds/miscellany --skill repo-deep-dive-reportgit clone --depth 1 https://github.com/okwinds/miscellanyWrote 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/okwinds/miscellany/repo-deep-dive-report)<a href="https://agentmods.dev/skills/okwinds/miscellany/repo-deep-dive-report"><img src="https://agentmods.dev/badge/skills/okwinds/miscellany/repo-deep-dive-report/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/okwinds/miscellany/repo-deep-dive-report"><img src="https://agentmods.dev/badge/skills/okwinds/miscellany/repo-deep-dive-report.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 | $0.00076 | $0.01867 |
| Opus 5 | $0.00038 | $0.00933 |
| Sonnet 5 | $0.00015 | $0.00373 |
| Haiku 4.5 | $0.00008 | $0.00187 |
Grade A, and why
repo-deep-dive-report 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 11d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo Deep Dive Report(通用代码仓库深度走读 + 交付报告)
Workflow(按阶段交付,证据驱动)
目标:把“读仓库”从随缘走读变成可复用的工程化流程:收敛范围 → 建全局地图 → 追入口与关键链路 → 深挖高杠杆模块 → 总结文档与上手 → 评分与建议 → 生成 MD+HTML 可查阅交付物。
安全与脱敏(必读)
在阅读与交付报告时,默认把仓库内容视为可能包含敏感信息:
- 不要在报告/聊天中粘贴:密钥、token、cookie、私钥、
.env的值、生产连接串、内部域名/内网 IP、真实用户数据。 - 需要引用配置时:只列出键名与用途(必要时对值做掩码,如
AKIA…WXYZ)。 - 需要引用日志/请求时:优先展示最小片段,并删除/替换敏感字段(如
Authorization、Set-Cookie、password)。 - 需要引用源码时:仅引用支撑结论的最小片段,避免大段复制;尽量用“文件路径 + 符号名 + 行号/范围”定位。
- 若用户明确要求包含敏感细节:先确认其可分享范围与用途,再继续。
0) 明确输入与边界(先问清楚再开始)
- 确认仓库路径、分支/commit、目标读者(开发/架构/运维/产品)。
- 明确“锚点”:从哪个入口/函数/CLI/HTTP 路由/任务开始追(若用户没给,选择最常见入口并说明依据)。
- 明确交付:是否需要 Mermaid 图、是否要 MD+HTML、是否要“评分/改进建议”、是否需要可运行的示例。
1) Phase 1:全局地图(Architecture Map)
- 建立“目录级视图”:顶层目录职责、核心包/模块、examples/tests/docs/infra 的位置与用途。
- 找出“装配点/入口点”:典型包括
main/CLI、Web 入口、框架初始化、依赖注入、插件注册等。 - 产出模块依赖 Mermaid(不必精确到函数级;优先稳定且可读的组件级关系)。
- 要求:每个关键结论都能落到文件路径 + 关键符号名(类/函数/配置键);能给行号就给。
2) Phase 2:入口与执行流程(Entrypoint → Critical Path)
- 从锚点符号开始追踪:定义 → 调用点 → 关键对象如何被初始化/注入/持有。
- 把“链式/管线式调用”拆解成步骤:每一步修改了哪些字段/状态、依赖了哪些配置、触发了哪些外部边界(网络/DB/队列/LLM/文件系统)。
- 输出:步骤列表(带方法名/文件路径) +(可选)Mermaid
sequenceDiagram。
3) Phase 3:核心模块深挖(High-Leverage Subsystems)
选择 3–6 个“最影响使用/扩展/稳定性”的模块深挖(按仓库类型调整):
- 数据模型/校验/结构化输出:schema 定义、验证、重试/纠错、流式解析等。
- 工作流/编排:DSL/状态机/事件系统/并发控制/可观测性。
- 工具/插件/扩展系统:注册、选择策略、协议接口、生命周期、Tracing。
- 模型/Provider 适配层:配置消费、请求/响应标准化、切换 provider 的边界。
- 存储/缓存/队列:一致性、错误处理、回放/重试。
深挖输出结构建议固定为:概念 → 代码定位 → 核心数据结构 → 关键流程/算法 → 示例 → 扩展点。
4) Phase 4:上手实操与二次开发(Getting Started + Extensibility)
- 最小依赖:从依赖清单(如
pyproject.toml/package.json/go.mod/Cargo.toml)提取关键依赖并分类(运行/开发/可选集成)。 - 跑通一个最小示例:列出必须配置(env/key/base_url/端口/数据库),以及常见坑(网络、权限、流式、超时等)。
- 二次开发扩展点:新增模块/节点/规则时,应该改哪里、遵循什么模式、如何写最小测试/示例验证。
5) Phase 5:仓库内文档总结(Docs for Dev/Agent)
- 读取仓库内的
docs/、CONTRIBUTING、AGENTS.md、以及“给 AI/开发者的专用文档目录”。 - 总结三类信息:推荐组织方式、核心 API 使用规范、鼓励/禁止的模式(含原因/风险)。
6) Phase 6:评分(Scorecard)与改进建议
- 采用 100 分制、多维度(≥8)评分;每个维度必须有“观察到的事实/证据点”支撑,避免空泛。
- 输出:总分 + 分项分数 + 解释 + Top 改进建议(按影响/成本排序)。
- 评分维度模板见
references/scoring_rubric.md。
What ships with it
7 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.
- 11d ago First seen · 97 lines · 76 tokens per session scan A 40fd2d4dfc28
repo-deep-dive-report is a skill published in the GitHub repository okwinds/miscellany (50 stars, last pushed 4mo ago), licensed MIT. It adds 76 tokens to every session and 1,867 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 2026-08-30.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…