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/mh4gf/claude-code/create-linear-issuenpx skills add MH4GF/claude-code --skill create-linear-issuegit clone --depth 1 https://github.com/MH4GF/claude-codeWhat 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 | $0.00108 | $0.02613 |
| Opus 5 | $0.00054 | $0.01307 |
| Sonnet 5 | $0.00022 | $0.00523 |
| Haiku 4.5 | $0.00011 | $0.00261 |
Grade A, and why
create-linear-issue 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 yesterday.
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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
create-linear-issue
ユーザーの一行の意図を、superpowers:brainstorming で固めてから Linear issue として起票する skill。issue body は brainstorming の議論結果から直接組み立てる。Linear MCP server linear-mh4gf 経由で書き込む。
Symphony 系の運用へ乗せる前提で、起票先は Linear workspace の project と1対1に対応する。Symphony が次の poll で拾うことを期待する。
なぜ brainstorming を必須にするか
brainstorming skill の哲学に従う。「simple な issue こそ未検証の前提が無駄な実装を生む」。issue の Outcome / Why / 完了条件 を曖昧なまま起票すると、Symphony が拾った後の実装ワーカーは推測で動く羽目になる。brainstorming で意図を固めれば、その議論結果が issue body の素材になる。
使用する MCP server
linear-mh4gf という名前で登録された Linear MCP server を使う。ツール命名は mcp__linear-mh4gf__* の prefix。代表的に次を使う。
mcp__linear-mh4gf__list_projects— project 一覧と ID 解決mcp__linear-mh4gf__list_teams— team 一覧と ID 解決mcp__linear-mh4gf__list_issues— 重複検知mcp__linear-mh4gf__save_issue— 起票
手順
1. superpowers:brainstorming で意図を固める
Skill ツール経由で superpowers:brainstorming を起動し、ユーザー の一行の意図を渡す。brainstorming は次を実施する。
- project context の探索 (関連ファイル / 先行事例 / 既存 issue)
- clarifying questions (one at a time)
- 2-3 approaches の提示と user 選択
- design sections の提示と user 承認
注意点:
- brainstorming skill の標準フローには「Write design doc → spec self-review → User reviews spec → Invoke writing-plans skill」がある
- 本 skill 経由では design doc を別ファイルとして書かない。議論結果は直接 issue description へ統合する
- 別ファイル書き出しと writing-plans 起動が起きそうになったら、ユーザー へ確認して スキップ する
- 確認文言: 「create-linear-issue 経由なので design doc 書き出しと writing-plans を スキップ し、議論結果から直接 Linear 起票へ進む」
理由: bg session の作業 workspace は origin/main の depth=1 clone なので、scraps/open/ 等へ書いた新規ファイルを bg session 側から読めない。issue body だけが情報源になる前提で組む。
2. project と team を解決する
mcp__linear-mh4gf__list_projects で project 一覧を取得する。ユーザー が指定した project (または会話の文脈で自明な project) を name で絞り込んで ID を得る。複数該当した時は AskUserQuestion で確定する。
その project の team ID も取得する。project レスポンスに teams が含まれていればそれを使う。含まれない時は mcp__linear-mh4gf__list_teams で解決する。
3. 重複を検索する
brainstorming で出てきたキーワード (1〜2語) で既存 issue を検索する。
mcp__linear-mh4gf__list_issues(query="<keyword>", project="<projectId>")
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.
- yesterday First seen · 135 lines · 108 tokens per session scan A 8258f7400f54
create-linear-issue is a skill published in the GitHub repository MH4GF/claude-code (2 stars, last pushed 2d ago), licensed MIT. It adds 108 tokens to every session and 2,613 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…