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/recca0120/code-quest/code-quest-reviewnpx skills add recca0120/code-quest --skill code-quest-reviewgit clone --depth 1 https://github.com/recca0120/code-questWhat 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 | $0.00096 | $0.01709 |
| Opus 5 | $0.00048 | $0.00855 |
| Sonnet 5 | $0.00019 | $0.00342 |
| Haiku 4.5 | $0.00010 | $0.00171 |
Grade A, and why
code-quest-review 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Quest 專案特定 Code Review
除通用 /code-review skill 的審查維度外,本專案額外檢查以下項目。
Import
- import 放在檔案最頂部,不要 inline import(函式中間寫 import)
- Node.js built-in import(
node:path,node:fs)放最上方
isolatedDeclarations
summoner package 開啟了 isolatedDeclarations: true,影響:
- exported 變數必須有顯式型別標注 — 不可依賴推導,這不是冗餘
- schema 檔(
schemas.ts、launch-options.ts)的縮寫型別別名(Opt、Str、Num、Bool、Unk、Loose)是為了簡化這些必要標注,屬合理設計,不應移除 - 審查時看到 schema export 帶顯式型別,不要標為「冗餘型別標注」
Zod
.passthrough()/.loose()→ 改z.looseObject()(Zod v4 deprecated)- shared schema 只有一個 package 使用 → 搬到該 package
payload as { ... }inline type assertion → 改用 zod schema parse:- 先查 shared schemas 有沒有現有 schema 可用
- 沒有才新建,放 shared 讓前後端共用
- 不要 inline
z.looseObject({...}).parse(payload)— 那只是換一種 inline,應該抽成 named schema
跨 Package 對齊(shared / summoner / server / client)
- server
emitter.on('event', ...)的 event name 跟 sharedsocket-events.ts定義是否一致 - server
ch.sendRequest('event', ...)的 event name 跟 adapterREQUEST_MAPPINGS是否一致 - adapter
transformControlRequest產出的 event name 跟 server handler 訂閱的是否一致 - client handler on map 的 event name 跟 server emit 給 client 的是否對齊
- shared
ClientToServerEvents/ServerToClientEvents定義跟實際 emit/on 是否同步
summoner(CLI adapter)
REQUEST_MAPPINGS是否涵蓋所有ch.sendRequest呼叫的 event name- adapter transform 每個 case 是否都有 named function(不用 inline arrow)
isRecord()等 util 是否集中在utils.ts,不重複定義ProcessRunner終止方法只有kill()(底層呼叫 handle 的abort())— 不要再加abort()wrapperconsole.debug/console.log→ 改用logger(pino),注意 pino API 第一個參數是 object:logger.debug({ err }, 'message')
server handler
- middleware 是否正確:
- 需要 channel 且有 callback →
withError(withChannel(handler)) - 需要 channel 無 callback →
withChannel(handler) - 需要 socket →
withSocket(handler) - 不需要 channel → 直接註冊
- 需要 channel 且有 callback →
- handler 使用
ch.sendRequest('event', payload)不直接用 protocol subtype - handler 使用 named function(不用 arrow)
- handler 內
respondToRequest只在 auto-respond 或 CLI-initiated event 使用
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 · 116 lines · 96 tokens per session scan A d8d89f59c76e
code-quest-review is a skill published in the GitHub repository recca0120/code-quest (11 stars, last pushed 2mo ago), licensed MIT. It adds 96 tokens to every session and 1,709 once invoked, about $0.0005 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…