Borrowing it
Nothing to install: this file belongs to suisya-systems/claude-org-ja. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/suisya-systems/claude-org-ja/main/.claude/skills/goal-setup/SKILL.mdgit clone --depth 1 https://github.com/suisya-systems/claude-org-jaWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/suisya-systems/claude-org-ja/goal-setup)<a href="https://agentmods.dev/skills/suisya-systems/claude-org-ja/goal-setup"><img src="https://agentmods.dev/badge/skills/suisya-systems/claude-org-ja/goal-setup/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/suisya-systems/claude-org-ja/goal-setup"><img src="https://agentmods.dev/badge/skills/suisya-systems/claude-org-ja/goal-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00209 | $0.02179 |
| Opus 5.5 | $0.00084 | $0.00872 |
| Sonnet 5.5 | $0.00042 | $0.00436 |
| Haiku 4.5 | $0.00021 | $0.00218 |
Grade A, and why
goal-setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
goal-setup: ゴール台帳を対話で書く
/work-discovery は、オペレーターが書いたゴール台帳の条項に当たる Issue だけを条項順に提案する。
台帳の無いプロジェクトからは候補が出ず、書式が崩れた台帳も候補ゼロになる。本スキルは、その台帳を人間との対話で作る・直す。
- 書式の正本:
registry/goals/README.md(例:registry/goals/example.md) - 設計:
docs/design/work-discovery-triage.md§12.3 - 書式検証:
tools/work_discovery_goals.py validate(scan と同じパーサで読む。ここを通らない台帳は保存しない)
起動主体は窓口。台帳はオペレーターのローカルファイル(git 管理外)なので、commit・PR はしない。 ゴールの中身は人間が決める。窓口は候補を推定して示すが、条項の採否・文言・順番はすべて人間の答えで確定させる。
Step 1 — 対象リポジトリを決める
引数($ARGUMENTS)の通称を GitHub の owner/repo に解決する。owner/repo 形式ならそのまま使う。
python3 tools/work_discovery_repos.py --format json
included[] の nickname と引数を照らして repo を取る。
- 引数が無い、または一致が無い・複数あるときは、
included[]の通称一覧を示して聞き返す。 opted_out[](triage 列で除外)にある通称なら、台帳を書いても候補は出ないことを伝え、先にregistry/projects.mdの triage 列を戻すかを聞く。skipped[](パスが GitHub URL でない等。reason付き)にある通称なら理由を伝え、owner/repoを直接教えてもらう。- 台帳のパスは
registry/goals/<owner>/<repo>.md(小文字)。
Step 2 — 既存台帳を確認する
python3 tools/work_discovery_goals.py validate --repo <owner>/<repo>
出力は 1 行の JSON(status が ok なら exit 0、それ以外は exit 1)。
unset→ 新規作成モード。ok→ 改訂モード。台帳ファイルを Read し、今の条項(G1 から順に見出しと unmet if)を人間に見せて、何を変えたいか(追加・削除・順番・文言)を聞く。error→ 修復モード。errorの内容(例:G2: no 'unmet if:' line)をそのまま伝え、台帳を Read して直し方を提案する。case mismatchはファイル名を小文字に直す話なので、その旨を伝える。
Step 3 — ゴール候補を推定して提示する
新規作成モードと、改訂で条項を足すときに行う。材料は 2 つだけ(読み取りのみ):
gh repo view <owner>/<repo>
gh issue list --repo <owner>/<repo> --state open --limit 100 --json number,title,labels
README の目的と、open Issue のまとまり(同じ困りごとを指す Issue 群)から、ゴール候補を 3〜5 個に絞って示す。 各候補は「目指す状態 1 行 + 根拠になった Issue 番号 2〜3 個」。 Issue をそのまま条項にしない。条項は「状態」であり、Issue はその未達を解消する仕事である。
Step 4 — 質問して条項を固める
候補を叩き台に、1 条項ずつ短く聞く(まとめて 5 問を並べない):
- 何を目指すか: 見出しになる 1 行(例「利用者がセットアップで詰まらない」)。
- 何が起きていたら未達か:
unmet ifを 1 行以上。Issue が 1 件出れば当たるくらい具体的に(例「README の手順どおりに進めて失敗する報告が open のまま残っている」)。「品質が低い」のような判定できない文は、どんな報告・状態を指すかを聞き返して具体化する。 - 順番: 全条項が出そろったら並びを見せ、「上にある条項ほど優先して提案されます。この順で合っていますか」と確認する。
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.
- 12d ago Changed · -2 lines 7a17c7264453
- 29d ago First seen · 106 lines · 209 tokens per session scan A 0d4b1dff8c4b
goal-setup is a skill published in the GitHub repository suisya-systems/claude-org-ja (5 stars, last pushed 5d ago), licensed MIT. It adds 209 tokens to every session and 2,179 once invoked, about $0.0008 per session on Opus 5.5. 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 2026-10-01.
Other skills, from other repositories
board
Read and write the workspace BOARD.md (shared task board for agents + Val). Wraps bin/board, a small Python CLI that preserves the markdown schema and appends to the activity log automatically. Use this whenever an agent proposes, claims, or finishes work that should be visible to the rest of the roster.
ai-agent-job-marketplace
The job marketplace where bots hire bots. Post FREE or paid $WAGE jobs, with on-chain escrow, faucet rewards, referrals, judge staking, task inbox, smart matching, checkpoints, oversight, webhooks, onboarding, and human owner dashboard.
agent-freelance-bounty-marketplace
Earn USDC completing bounties, post jobs, join multi-agent raids, build reputation, rank up. AI agent freelance marketplace with x402 escrow on Solana. Free SOL airdrop on signup. Guilds, ranks, vouching, disputes, Castle Town, leaderboard.
agent-job-marketplace-with-bidding
Agent-to-agent marketplace MVP. Agents post jobs, bid, contract, submit deliverables, and leave reviews. Payments are off-platform (crypto) in v1.
advise-engineering-technical-leadership
Technical leadership guidance for engineering teams, architecture decisions, and technology strategy. Use when assessing technical debt, scaling engineering teams, evaluating technologies, making architecture decisions, establishing engineering metrics, or when user mentions CTO…
agent-team-collaboration-marketplace
The marketplace for AI agents to form teams and collaborate on projects. Find teammates, join teams, build together.