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/docs-lookupnpx skills add ProgrammerAnthony/Expert-Coding-Harness --skill docs-lookupgit 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 | $0.00173 | $0.01225 |
| Opus 5 | $0.00086 | $0.00613 |
| Sonnet 5 | $0.00035 | $0.00245 |
| Haiku 4.5 | $0.00017 | $0.00122 |
Grade A, and why
docs-lookup 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
文档查询
铁律：查文档，不靠记忆。 当用户询问任何库、框架或 API 的用法时，必须通过 Context7 MCP 获取实时文档，而非依赖训练数据给出可能已过时的答案。
何时触发
- 用户询问某个库或框架的用法（"React 的 useEffect 怎么用？"）
- 用户要求生成依赖特定库的代码（"帮我写一个 Prisma 查询"）
- 用户询问 API 参考或配置方式（"Next.js middleware 怎么配置？"）
- 用户提到了具体的库名（React、Vue、Next.js、Prisma、Supabase、Tailwind 等）
- 用户询问某个库的特定版本行为（"Next.js 15 的 App Router"）
工作流
第一步：解析库 ID
调用 Context7 MCP 的 resolve-library-id 工具：
libraryName：从用户问题中提取的库名（如Next.js、Prisma、Supabase）query：用户的完整问题（提升匹配相关性）
必须先获得有效的 Context7 库 ID（格式为 /org/project）才能进入下一步，禁止直接调用 query-docs。
第二步：选择最佳匹配
从解析结果中按以下优先级选择：
| 优先级 | 判断依据 |
|---|---|
| 1 | 名称与用户所问库完全匹配 |
| 2 | Benchmark 分数更高（100 分为满分） |
| 3 | Source reputation 为 High 或 Medium |
| 4 | 若用户指定了版本号，优先选版本专属 ID |
第三步：获取文档
调用 Context7 MCP 的 query-docs 工具：
libraryId：第二步选出的库 ID（如/vercel/next.js）query：用户的具体问题，越具体越好
限制：每个问题最多调用 query-docs 3 次。3 次后仍不确定，说明情况并用已有最佳信息作答，不得猜测。
第四步：回答用户
- 用获取到的实时文档内容回答问题
- 包含文档中的相关代码示例
- 涉及版本差异时明确标注（如"在 Next.js 15 中..."）
示例
示例 1：Next.js middleware 配置
- 调用
resolve-library-id，libraryName: "Next.js"，query: "Next.js middleware 怎么配置？" - 从结果中选
/vercel/next.js（名称匹配 + 高分） - 调用
query-docs，libraryId: "/vercel/next.js"，query: "middleware configuration" - 用返回的文档和
middleware.ts示例回答
示例 2：Prisma 关联查询
- 调用
resolve-library-id，libraryName: "Prisma"，query: "如何查询关联关系？" - 选
/prisma/prisma - 调用
query-docs，query: "query with relations include select" - 返回 Prisma Client 的
include/select模式与代码示例
示例 3：Supabase 认证方式
- 调用
resolve-library-id，libraryName: "Supabase"，query: "Supabase 有哪些认证方式？" - 选 Supabase 官方库 ID
- 调用
query-docs，汇总认证方法并给出最小示例
最佳实践
| 原则 | 说明 |
|---|---|
| 具体查询 | 用用户完整问题作为 query，比通用词更准确 |
| 版本感知 | 用户提到版本时，优先选版本专属库 ID |
| 官方优先 | 多个匹配时优先选官方/主包，而非社区 fork |
| 不传密钥 | 在调用 resolve-library-id 或 query-docs 前，移除问题中的 API Key、密码、Token 等敏感信息 |
反模式
| 反模式 | 后果 |
|---|---|
| 跳过 resolve-library-id 直接猜测库 ID | query-docs 返回错误或无关文档 |
| 用训练数据直接回答库 API 问题 | 给出已过时或错误的 API 用法 |
| query 过于模糊（如只写库名） | 返回的文档片段不相关 |
| 超过 3 次仍继续调用 | 浪费 context，应直接说明不确定性 |
| 将含敏感数据的问题原文发送 Context7 | 泄露用户凭证 |
What ships with it
1 file 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 · 95 lines · 173 tokens per session scan A 82e5b967d24a
docs-lookup is a skill published in the GitHub repository ProgrammerAnthony/Expert-Coding-Harness (235 stars, last pushed 3mo ago), licensed MIT. It adds 173 tokens to every session and 1,225 once invoked, about $0.0009 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…