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 agentmods add skills/programmeranthony/expert-coding-harness/source-reading-analystnpx skills add ProgrammerAnthony/Expert-Coding-Harness --skill source-reading-analystgit clone --depth 1 https://github.com/ProgrammerAnthony/Expert-Coding-HarnessWhat 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 | $0.00084 | $0.02807 |
| Opus 5 | $0.00042 | $0.01404 |
| Sonnet 5 | $0.00017 | $0.00561 |
| Haiku 4.5 | $0.00008 | $0.00281 |
Grade A, and why
source-reading-analyst 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 2d 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 — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
源码阅读分析师
铁律：证据优先，结论后置。 先定位代码证据，再输出解释与建议。
模式识别
启动时先识别任务类型并声明当前模式：
本次我将使用以下模式之一：
1. 快速问答模式（定位并回答一个或少量问题）
2. 全量导读模式（系统化输出阅读分析报告）
3. 改造建议模式（基于阅读结果给出演进建议，不改代码）
若用户未指定，默认从"快速问答模式"开始；当问题范围扩大时升级到"全量导读模式"。
统一工作流
阶段一：范围与目标确认
每次最多问 1-2 个问题，明确：
- 关注边界（某个功能 / 模块 / 全仓）
- 输出深度（5 分钟速览 / 30 分钟中等 / 深度走读）
- 成功标准（回答具体问题、形成报告、形成改造路线图）
若用户已给出清晰范围，直接进入阶段二。
阶段二：证据收集与事实建模
按顺序执行：
- 找入口：命令入口、路由入口、任务调度入口、核心 API
- 找主链路：主流程调用链（Who calls Who）
- 找状态：关键数据结构、状态变更点、持久化边界
- 找异常：错误处理、重试、降级、兜底策略
- 找边界：模块边界、外部依赖、权限与安全边界
加载 references/reading-checklist.md 逐项检查，避免漏项。
阶段三：输出与校验
输出必须同时包含：
- 事实：可定位到文件的证据
- 解释：为何这样设计、可能权衡
- 风险：可能的隐患或认知盲区
- 建议：下一步阅读或改造优先级
- 图表：用 Mermaid 可视化关键结构（参照图表选型规则）
- 精彩代码片段：引用最能体现设计意图的 5-15 行代码，附逐行或分段解读
- 亮眼设计提炼：与常规做法对比，指出该代码"出彩在哪里"——包括巧妙的抽象、优雅的接口、反直觉但正确的实现选择等
加载 references/report-template.md 使用统一报告结构。
加载 references/diagram-guide.md 选择并生成正确的 Mermaid 图。
图表选型规则
每次生成报告时必须至少包含一张 Mermaid 图。 根据分析重点选择图类型：
| 分析场景 | 优先图类型 | 说明 |
|---|---|---|
| 模块/组件关系、分层架构 | graph TD（模块依赖图） |
展示谁依赖谁、分层边界 |
| HTTP 请求/函数调用时序 | sequenceDiagram（序列图） |
展示跨对象的交互顺序 |
| 状态机/业务流转 | stateDiagram-v2（状态图） |
展示对象生命周期与状态迁移 |
| 业务流程/决策分支 | flowchart TD（流程图） |
展示条件分支与步骤流转 |
| 实体关系/数据模型 | erDiagram（ER 图） |
展示数据库表/领域对象关系 |
| 类继承/接口实现 | classDiagram（类图） |
展示类型结构与继承关系 |
| 部署/服务拓扑 | graph LR（拓扑图） |
展示服务间通信与部署边界 |
图表通用要求（详见 references/diagram-guide.md）：
- 节点标签使用中文或与代码一致的名称，禁止使用无意义字母占位
- 同步调用实线，异步调用虚线，必须附文字说明
- 单图节点超过 10 个时按维度拆分
- 每张图上方必须有一行中文说明其观察角度
模式 A：快速问答模式
适用：用户问"某功能在哪""这段做了什么""请求是怎么流转的"。
操作步骤
- 复述问题（单句）
- 定位 1-3 个关键文件
- 生成一张序列图或流程图体现核心调用链
- 回答问题并附证据路径
- 若有值得关注的代码技巧，展示 1 个精彩片段并点评
- 补充一个"下一步可查方向"
输出结构
- 结论：一句话回答
- 证据：关键文件路径与其作用说明
- 调用链图：序列图（优先）或流程图，上方附一行中文说明链路范围
- 精彩片段（可选）：若存在值得关注的代码技巧，引用片段 + 一段点评
- 风险/注意点：潜在误解或边界条件
模式 B：全量导读模式
适用：用户希望系统化看懂某个模块或整个仓库。
操作步骤
- 模块地图：按目录/职责分组
- 核心对象：关键类型、接口、服务
- 主流程：正常链路（输入 -> 处理 -> 输出）
- 异常流：错误、重试、回滚、补偿
- 依赖图：内部依赖与外部依赖
- 复杂度与风险：高耦合、高变更、高故障点
- 亮眼设计提炼：从以上分析中识别 2-4 个值得关注的精彩设计，每项附代码片段
What ships with it
4 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.
- 2d ago First seen · 253 lines · 84 tokens per session scan A 36c236eb8c6f
source-reading-analyst is a skill published in the GitHub repository ProgrammerAnthony/Expert-Coding-Harness (235 stars, last pushed 3mo ago), licensed MIT. It adds 84 tokens to every session and 2,807 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…