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/lee-w/maigo/pr-context-cachenpx skills add Lee-W/maigo --skill pr-context-cachegit clone --depth 1 https://github.com/Lee-W/maigoWhat 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 | $0.00058 | $0.01099 |
| Opus 5 | $0.00029 | $0.00549 |
| Sonnet 5 | $0.00012 | $0.00220 |
| Haiku 4.5 | $0.00006 | $0.00110 |
Grade A, and why
pr-context-cache scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Context Cache
Owner Agent: Raana
Consumers: /maigo:review step 1
Why this skill exists
/maigo:review 的第一步是 Raana 抓 PR context。「re-review」（同一個 PR 改完再跑一次）
時這些資料幾乎沒變——重抓只是浪費時間。第一次 fetch 後 cache 到本次的 review rubric
檔開頭的機讀區段，re-review 偵測同 source 且 diff sha 未變 → 直接還原，跳過全部
gh / git 重抓。rubric 檔路徑不再固定：省略 --rubric 時 script 會依 source
呼叫 scripts/artifact_path.py
算出 .maigo/review-rubric-<id>.md（歸屬規則見
artifact-ownership）。
怎麼跑
機械流程由 script 代勞（cache 偵測 / 驗證 / fetch / truncate / 寫檔一條龍）：
python3 "${CLAUDE_PLUGIN_ROOT:-.}/scripts/pr_context_cache.py" <source> \
[--rubric PATH] [--base main]
<source>：GitHub PR URL / PR 編號（需要 gh CLI）、本地 branch 名、或 commit range- 在 maigo repo 自身工作時，直接
python3 scripts/pr_context_cache.py即可 - 省略
--rubric是預設用法——script 自動算路徑；只有需要覆寫既有檔案時才傳--rubric
stdout 第一行是 cache_hit: true|false，第二行 rubric: <path>，其後是 cache 區段全文——
含 Source / PR number / Title / Body（截 500 行）/ Linked issues / CI status /
Diff stat / Review threads（inline review thread，含 resolve 狀態）/ Review
summaries（gh pr view --json reviews）/ Conversation comments（gh pr view --json comments） / Diff sha / Full diff（截 2000 行）。
Review threads / summaries / comments 只在 <source> 是 PR 時抓（branch / range
diff 沒有對應的 GitHub review thread 可抓）。未解決（[OPEN]）的 thread 在輸出
裡會被特別標出——下結論前先檢查這些 thread 對照目前 diff 是否已經處理，
避免漏看 reviewer 留下但尚未收斂的架構意見（真實事故：只抓 diff + PR body +
reviewDecision，漏看某 PR 上一位 reviewer 對 isinstance-based type-switch 設計
留下的 OPEN thread，直到使用者問「有沒有看 TP 說了什麼」才補回）。
行為摘要
- cache hit（Source 相同且 diff sha256 未變）→ 印出快取區段，不碰網路（除了重算 sha 的那次 diff）
- cache miss → 重抓全部欄位，寫回 rubric 開頭
<!-- pr-context-cache:start v1 -->…<!-- pr-context-cache:end -->區段 （無檔案 → 建立；無區段 → prepend；有舊區段 → 整段取代）
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 · 69 lines · 58 tokens per session scan A 915e1dac5f58
pr-context-cache is a skill published in the GitHub repository Lee-W/maigo (14 stars, last pushed 9d ago), licensed MIT. It adds 58 tokens to every session and 1,099 once invoked, about $0.0003 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…