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/github-title-descriptionnpx skills add Lee-W/maigo --skill github-title-descriptiongit 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 | $0.00095 | $0.03140 |
| Opus 5 | $0.00048 | $0.01570 |
| Sonnet 5 | $0.00019 | $0.00628 |
| Haiku 4.5 | $0.00010 | $0.00314 |
Grade A, and why
github-title-description 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Title & Description
Owner Agent: Tomori（/maigo:describe-pr step 2——orchestrator 前置抓料後交給燈套用）
Consumers: /maigo:describe-pr
Why this skill exists
PR title / description 是 reviewer 對這次變更的第一印象。常見的失敗：
- title 抄最後一個 commit message（內部視角，reviewer 看不出價值）
- description 只寫「改了 X / Y / Z」（檔案清單 reviewer 自己看 diff 就有）
- 沒講為什麼（reviewer 得逆向工程動機）
- 沒講怎麼驗證（reviewer 得自己想 test scope）
這個 skill 把這四件事變成有結構的 process。
Inputs（caller 必須給 / 自己抓的東西）
- Base branch（通常
main；caller 可覆寫） - Branch commits：
git log <base>..HEAD --pretty=format:'%h %s%n%b' --no-merges - Branch diff stat：
git diff <base>...HEAD --stat - Branch diff：
git diff <base>...HEAD（必要時 truncate）——描述淨交付，不是過程： 若 branch 曾經試過一個設計、後來整段 revert（例如先加了某組 flag + UI，後來為了 auto-detect 拆掉），diff 已經反映拆掉後的淨狀態，草稿只描述這個最終形狀，不提被拆掉的中途嘗試——squash merge 會把整段歷史壓平，reviewer 只在乎最終長什麼樣。用git diff <base>...HEAD（或明確要求 working tree 版本git diff <base>，含未 commit 的收尾）取料，不要餵 commit log 的話題給草稿—— commit log 會帶出被拆掉的中途嘗試痕跡。 - Repo commit-style 偵測（決定要不要參考既有 commit message 風格）：
偵測規則依
skills/commit-messageInputs 第 3 條（[tool.commitizen]/.cz.*/ commitlint 設定檔 → Conventional Commits；repo 有明文禁用 CC 的慣例 → 跟 repo 走自由格式；皆無訊號 → 預設 Conventional Commits）。 這只影響 commit message 風格參考；PR title 本身永不套type:prefix。 - PR template（若存在）：caller 在
.github/PULL_REQUEST_TEMPLATE.md（含大小寫變體與.github/PULL_REQUEST_TEMPLATE/目錄）找到的 template 內容。- 找到 → 以 template 結構作為描述框架，填入從 commits / diff 萃取的內容，取代預設的 Why / What / Test Plan 結構
- 找不到 → 用本 skill 預設結構
Title 規則（user-impact 句子）
- 一句話、user 視角：寫「使用者 / reviewer 看完會知道這 PR 做了什麼」
- 開頭大寫（英文）；中文無此限
- 不加 conventional-commits prefix（不要
feat:、fix:） - 長度建議 ≤ 72 字（GitHub UI 一行不截斷）
- 不寫檔名：「Refactor
auth.py」← bad；「Reject empty emails before hashing」← good - 動詞開頭 比名詞開頭更直接（「Add X」、「Fix Y」、「Allow Z」）
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 · 210 lines · 95 tokens per session scan A df5726fe722c
github-title-description is a skill published in the GitHub repository Lee-W/maigo (14 stars, last pushed 9d ago), licensed MIT. It adds 95 tokens to every session and 3,140 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…