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/interview-knowledge-tracknpx skills add ProgrammerAnthony/Expert-Coding-Harness --skill interview-knowledge-trackgit 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 | $0.00154 | $0.01792 |
| Opus 5 | $0.00077 | $0.00896 |
| Sonnet 5 | $0.00031 | $0.00358 |
| Haiku 4.5 | $0.00015 | $0.00179 |
Grade A, and why
interview-knowledge-track 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interview Knowledge Track（面试知识点三阶段追踪）
权威切片与参考
- 分步执行的详细指令以本 skill 目录下
prompts/为唯一必需依据。 - 若工作区里另有用户自维护的「架构/面试」长提示词，仅可在不冲突时作语气参考；非必需，也不假定其路径或文件名。
目标与边界
- 目标：用三条英文命令驱动「拆知识点 → 按点检索沉淀 → 结合候选人自述文本做架构+面试合成」，定位表述中的薄弱技术点。
- 输入：第一步仅使用用户粘贴内容，或用户显式给出路径并要求读取的文件；不假定、不自动加载工作区内任何其它文件。
- 写操作范围：默认只在用户约定的工作根目录（见下）内创建/更新
KB-INDEX.md与主题子目录下的 Markdown；不把本 skill 与任意「默认简历文件」绑定。
英文命令（用户口述即可）
| 命令 | 含义 |
|---|---|
split-knowledge |
第一步：拆分知识点，生成/更新索引 KB-INDEX.md |
research-topic |
第二步：对某一知识点检索，写入该主题目录下两个 MD，并回写索引状态 |
synthesize-topic |
第三步：在指定知识点目录下，依据索引原文 + 第二步产出，写「与本人经历绑定」的两份 MD |
别名（可选）：kp-split → split-knowledge；topic-research → research-topic；topic-synthesize → synthesize-topic。
工作根目录与文件命名
- 工作根目录：用户指定则用之；否则默认为项目根目录下
interview-knowledge-track/。 - 第一步产出：
<root>/KB-INDEX.md（用户可指定其他路径/文件名，但同一会话后续步骤必须能唯一定位该索引）。 - 主题目录：
<root>/NN-slug/，例如01-langchain。NN为两位序号，与知识单元表顺序一致；slug小写、连字符。 - 第二步文件（固定文件名）：
opensource-and-architecture.md— 开源/博客/论文检索 + 架构与模块拆解，全文落盘。interview-drill.md— 精准关键词检索 + 概念补充 + 追问与参考答案，全文落盘。
- 第三步文件（与第二步同主题目录，除非用户另指定）：
architecture-bound-to-resume.mdinterview-bound-to-resume.md
第一步索引契约（KB-INDEX.md）
生成或更新 KB-INDEX.md 时必须包含：
- 原文保留区：完整粘贴用户输入（或注明读取的文件路径 + 可选校验信息如段落范围/哈希），满足不丢失原信息。
- 知识单元表：每行至少包含：
序号、知识点名称、slug、来源原文摘录（精确到句）、状态、对应目录。 - 拆分规则：技术栈/框架/领域词拆为可独立检索单元；同一句话可对应多个单元（摘录可重复或附注「共现句」）。
- 元数据：生成日期、工作根路径。
状态枚举与回写规则
| 状态 | 含义 |
|---|---|
pending |
尚未执行第二步 |
researched |
第二步已完成：NN-slug/ 下已写入 opensource-and-architecture.md 与 interview-drill.md，且索引中 对应目录 已填写 |
synthesized |
第三步已完成：同目录下已写入 architecture-bound-to-resume.md 与 interview-bound-to-resume.md |
- 第二步完成后：将该知识点行的
状态改为researched，并写回对应目录（如01-langchain）。 - 第三步完成后：将该知识点行的
状态改为synthesized。
Agent 执行要点
split-knowledge
- 创建或更新
<root>/KB-INDEX.md，遵守上文契约。 - 聊天中仅给出路径、主题数量与 slug 列表等短摘要。
What ships with it
3 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 · 111 lines · 154 tokens per session scan A f824519312f5
interview-knowledge-track is a skill published in the GitHub repository ProgrammerAnthony/Expert-Coding-Harness (235 stars, last pushed 3mo ago), licensed MIT. It adds 154 tokens to every session and 1,792 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 2026-08-30.
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…