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 skills add thkt/dotclaude --skill scopinggit clone --depth 1 https://github.com/thkt/dotclaudeWrote 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/thkt/dotclaude/scoping)<a href="https://agentmods.dev/skills/thkt/dotclaude/scoping"><img src="https://agentmods.dev/badge/skills/thkt/dotclaude/scoping/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/thkt/dotclaude/scoping"><img src="https://agentmods.dev/badge/skills/thkt/dotclaude/scoping.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 | $0.00058 | $0.01209 |
| Opus 5.5 | $0.00023 | $0.00484 |
| Sonnet 5.5 | $0.00012 | $0.00242 |
| Haiku 4.5 | $0.00006 | $0.00121 |
Grade A, and why
scoping 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 18d 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.
What it actually says
/scoping - 要求と実装範囲の整理
要求・完了条件・検証方法と合意範囲を整理し、実装へ引き継げる Issue を作る。商品実装や /implement の起動はこの呼び出しに含めない。
確認できる事実は調査し、ユーザーにしか分からない事実や未確定の意図は早めに質問する。人の判断が必要な質問は回答を待って依存する作業を止め、独立した調査は続ける。スキルの一般的な進め方よりユーザーの明示指示を優先する。指示文を理由に確認や停止が必要な場合は、実際に読んだ文書のパスと該当文を示し、明示された条件と自分の解釈を区別する。
Phase 1: 入口
$ARGUMENTS は依頼本文か Issue 番号。対象 repo の指定がなければ現在のリポジトリを使い、元の依頼がなければ AskUserQuestion で何を実現したいかを尋ねる。指定された Issue・設計案・既存の合意と、今回に関係する README・開発方針を確認し、合意済みのことを聞き直さない。小さな変更と文書変更も対象に含める。中断・担当交代では Issue・下書きの決定と不足を、現在のコードと要求に照らして再開する。
Phase 2: 判断
${CLAUDE_SKILL_DIR}/../../rules/conventions/DOCUMENTS.md§ Read and retain に従い、対象 repo の関連 wiki と判断記録を選ぶ。${CLAUDE_SKILL_DIR}/../scribe/scripts/find_wiki_rule.ts docs/wiki <依頼の語> <触れそうなパス> --scene planのmatchedとscenesのページを読む。選んだページと判断記録を現行コード・合意と照合する。文書が無くても調査を続ける。- 次に決めることを定め、
${CLAUDE_SKILL_DIR}/references/sufficiency.mdの 6 つの問いで根拠・代替案・不確実さ・権限を確認する。事実で解ける不足は調べる。 - 意図・優先順位・許容範囲・権限が未確定なら、AskUserQuestion で選択肢と影響を示して質問する。仮説を先頭の選択肢に置く。判断を左右する根拠が変わったら再評価する。
- 既存の資料では判断できず、観測結果で方針が変わる場合だけ
${CLAUDE_SKILL_DIR}/references/experiment.mdの小さな実験を検討する。
Phase 3: 成果物
目的・範囲・完了条件・検証方法、合意と未解決事項を Issue または下書きにまとめる。再利用する根拠や長い検証結果が必要な場合だけ、${CLAUDE_SKILL_DIR}/references/session.md の保存と引き継ぎを行う。判断が固まったら DOCUMENTS.md § Read and retain で wiki と判断記録への影響を確かめる。判断記録が要るなら /dr の MADR テンプレートを使う。
要求の抜け・矛盾・曖昧さと、合意・根拠との一致を確認する。矛盾か偏りが残るときは critic-design による独立評価を行い、行わなかったときは未実施と記録する。
「案だけ」「公開しない」の指定ではローカル下書きまでに留める。Issue の公開・更新が依頼範囲にある場合だけ ${CLAUDE_SKILL_DIR}/references/issue.md の手順を使い、対象・主体・権限と公開後の本文・URL を確認する。スキルの選択や下書きの保存を公開許可に読み替えない。
完了時に Issue または下書き、合意範囲、必要な報告の版と共有状態、残る判断を伝え、実装へ引き継ぐ。
What ships with it
4 files 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.
- 18d ago First seen · 36 lines · 58 tokens per session scan A 40b2af8ff73c
scoping is a skill published in the GitHub repository thkt/dotclaude (12 stars, last pushed 17d ago), licensed MIT. It adds 58 tokens to every session and 1,209 once invoked, about $0.0002 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 2026-09-28.
Other skills, from other repositories
tech-debt
Track, categorize and prioritize technical debt across the codebase — scans for debt indicators, maintains a register.
feature-dev
Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review. Use this skill when the user asks to build a new feature, add functionality, or wants a methodical approach to implementation rather than…
github-triage
Read-only GitHub triage for issues AND PRs. 1 item = 1 background task (category: quick). Analyzes all open items and writes evidence-backed reports to /tmp/{datetime}/. Every claim requires a GitHub permalink as proof. NEVER takes any action on GitHub - no comments, no merges, no closes, no labels. Reports only.…
project-init
Interview-based project setup — generates CLAUDE.md, ROADMAP, .gitignore, .env.example from scratch. Use when: user says '/project-init', 'new project', 'project creation', 'project setup', 'project setup', 'new project', 'create project'. NOT for AI agent/harness configuration (use setup for that). Conversational…
project-overview
Use when the user wants a deterministic cross-project status map generated from registered projects' session handoffs. Triggers: '/project-overview', 'project map', 'overall status'. Reads /.claude/projects-registry.md (opt-in list), parses each project's memory/session-handoff-LATEST.md state-snapshot v1 block…
assess-pr
The /assess end-of-run offers - open a PR with the report, track the Top 3 Actions in the user's issue tracker, freeze the assessment into a CI gate, and file tool feedback. TRIGGER when the /assess orchestrator reaches the end-of-run offers; not a standalone user command.