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/llm-wiki-interviewnpx skills add ProgrammerAnthony/Expert-Coding-Harness --skill llm-wiki-interviewgit 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 | $0.00126 | $0.00788 |
| Opus 5 | $0.00063 | $0.00394 |
| Sonnet 5 | $0.00025 | $0.00158 |
| Haiku 4.5 | $0.00013 | $0.00079 |
Grade A, and why
llm-wiki-interview 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 3d 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
LLM Wiki Interview（合并技能）
铁律：raw/ 与 wiki/ 分工不同——写资料只按 Raw 层规范；把资料编译成可查询 Wiki 只按 Wiki 层规范，且 ingest 时不得改 raw/。
与两层文件的关系
| 阶段 | 目录与职责 | 完整规范 |
|---|---|---|
| Raw 层 | 只写 raw/：唯一检索总账 _research.md、basic/、blog/、assets/；不写 wiki/ |
references/raw-layer.md |
| Wiki 层 | 只读 raw/，读写 wiki/：实体/概念/摘要页、wiki/index.md、wiki/log.md、图片同步到 wiki/assets/ |
references/wiki-layer.md |
衔接：两层只通过同一份 raw/ 对齐——先（或并行由用户维护）在 raw/ 里按 Raw 层落料，再在用户要求「导入 / ingest / 编译 wiki」时按 Wiki 层把内容编译进 wiki/。
何时加载哪一份 reference
- 用户要做 关键词拆分、检索笔记、basic 长文、blog 编译、用户供稿、每轮 blog≤5 等：先读
references/raw-layer.md，并遵守其中自检清单。 - 用户要说 创建知识库、从 raw 导入 wiki、查询 wiki、lint、维护 index/log：先读
references/wiki-layer.md。 - 同一会话里先 raw 后 wiki：两段规范都可能在一次任务里用到；切换阶段时明确当前手是否允许写
raw/还是仅写wiki/。
核心理念（与 Wiki 层一致）
用 LLM 持续维护结构化 Markdown 知识库（wiki/），而不是每次提问只做一次性检索；raw/ 作为不可变来源层与面试向加工层（basic + blog），再经 ingest 进入 wiki/。更细的哲学与操作见 references/wiki-layer.md 开头与「三大操作」。
参考资源（必读顺序）
references/raw-layer.md— Raw 层全部规则与质量自检。references/wiki-layer.md— Wiki 层 ingest / query / lint、初始化目录、实战经验（含raw/blog全文块与「核心内容提取」何者为真）。
项目内说明与出处见同目录 README.md。
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.
- 3d ago First seen · 36 lines · 126 tokens per session scan A a4631c558a38
llm-wiki-interview is a skill published in the GitHub repository ProgrammerAnthony/Expert-Coding-Harness (235 stars, last pushed 3mo ago), licensed MIT. It adds 126 tokens to every session and 788 once invoked, about $0.0006 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
trulens-notebook-execution
Execute and display Jupyter notebooks for TruLens demos and quickstarts.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
master-yinguang
Use when user asks about 印光大师, 净土, 念佛, 持名念佛, 十念法, 摄耳谛听, 老实念佛, 信愿行, 带业往生, 仗佛慈力, 自力他力, 竖出横超, 往生, 极乐, 阿弥陀佛, 净土三经, 敦伦尽分, 闲邪存诚, 因果报应, 文钞, 一函遍复, or wants teaching in 印光大师 Yinguang's voice. Triggers include "印光"、"文钞"、"老实念佛"、"信愿行"、"带业往生"、"仗佛慈力"、"横超竖出"、"都摄六根"、"净念相继"、"敦伦尽分"、"闲邪存诚"、"因果"、"十念法"、"摄耳谛听"、"一函遍复"、"净土三经"、"往生" — invoke…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
obsidian-to-clew-import
Convert an Obsidian vault or wiki-linked markdown graph into a validated structured-learning graph package for Clew. Use when the user wants to inspect a vault, preview whether it imports cleanly, preserve explicit relation markers, choose only the few import settings that matter, and produce a fail-closed package…