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 thinkgit 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/think)<a href="https://agentmods.dev/skills/thkt/dotclaude/think"><img src="https://agentmods.dev/badge/skills/thkt/dotclaude/think/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/think"><img src="https://agentmods.dev/badge/skills/thkt/dotclaude/think.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 | $0.00082 | $0.04021 |
| Opus 5.5 | $0.00033 | $0.01608 |
| Sonnet 5.5 | $0.00016 | $0.00804 |
| Haiku 4.5 | $0.00008 | $0.00402 |
Grade A, and why
think 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 1mo 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/think - 設計探索
2 つ以上の案を critic-design の批判にかけ、生き残った案だけを構造化 plan にまとめる。plan は templates/plan.md の骨格で下書きファイルに書き出し、会話でも返す。永続化は /issue が issue の Plan 節へ移設して行う。
入力
$ARGUMENTS でタスク説明と調査の文脈を受け取る。空なら AskUserQuestion でユーザーに確認する。先頭行をタスクのタイトルとして扱う。
Phase 1: Why の確立
.claude/OUTCOME.md を読む。存在しない場合は /outcome で生成する。Why は 3 点で構成し、タスクが Bug のときは 4 点目として原因を足す。誰が何に困っているか、何を成功とみなすか、なぜ今やるか、Bug なら原因は何か。困りごとには根拠を添える。原因は再現手順やログなど根拠とともに特定し、原因が未確定なら設計へ進まず /research に回す。戻ってきた調査レポートに 仮説ログ 節があれば、それを原因の根拠として読む。設計はこの Why が $ARGUMENTS と会話から読めてから始める。曖昧なまま仮置きせず、AskUserQuestion で詰める。
${CLAUDE_SKILL_DIR}/../../rules/conventions/DOCUMENTS.md に従い、関連 wiki・DR と原本の適用条件・状態を現在の要求へ照合する。必要な文書更新を今回の合意範囲へ含め、実装と同じ評価へ渡す。
Phase 2: 設計探索
案は、実在するコードと既存の調査に照らしてから作る。手順 1 から 4 は、案が 1 つも無い状態で終える。
- 関連コードを読む。タスク、issue、調査レポートのいずれかがモック画像を参照しているなら、その画像も Read で開く。テキスト側に記載が無いことを、その要素が存在しない根拠にしない
- タスクの語から小文字ハイフン区切りの slug を作る。${CLAUDE_SKILL_DIR}/../research/scripts/find-prior-research.ts docs/research research .claude/workspace/research を実行する。該当候補の
pathを読む。aliasesは同内容の移行コピーを示し、異なる版は比較する。各箇所を ${CLAUDE_SKILL_DIR}/references/research-report-intake.md の表のとおり扱う。候補が 0 件なら調査レポートは無いものとして進む - reference_module の候補を探す。対象は画面の組か layer の組が一致する既存モジュールで、ドメインは問わない。もっとも近い 1 つを選び、他は名前を控える。結果は kind (module/no-module/new-shape) と理由で控える。一致が無ければ新規である理由を控える
${CLAUDE_SKILL_DIR}/../scribe/scripts/find_wiki_rule.ts docs/wiki <slug> <触りそうなパス> --scene planを実行し、matchedとscenesのページを読む。決まりごとは unit の切り方と files の選び方を決めるので、分割の後に読むと割り直しになる- 異なる視点 (動く最小解/構造と拡張性/開発体験) から 2 つ以上の案を生成する。独立した技術判断は 1 つの質問に束ねず、推奨とトレードオフを添えて別々に問う
- 案に
critic-designを起動する。プロンプトにタスクのタイトルを一字一句そのまま含め、結果は{ verdict: "GO" | "NO-GO", weaknesses: string[], actionable: string[] }の JSON オブジェクト 1 つで返させる - NO-GO は blocker をその場で解消してから進む。生き残った設計をトレードオフの根拠とともにユーザーに提示し、承認を待つ
- 承認後、技術判断に DR が必要か問う
Phase 3: Plan 生成
承認された設計を unit へ実装順で分解する。unit は独立して実装できる成果 1 つ分。結果は PLAN_SCHEMA 相当の JSON へ直列化する。
{ test_command, reference_module, units: [{ id, goal, contract, files: string[], tests: [{ id, name }], seam }] }
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.
- 1mo ago Changed · +6 lines fc11e3a688f3
- 1mo ago Changed f215309225f1
- 1mo ago Changed · +1 lines 6c393d28f794
- 1mo ago First seen · 104 lines · 82 tokens per session scan A cfe24a58592c
think is a skill published in the GitHub repository thkt/dotclaude (12 stars, last pushed 25d ago), licensed MIT. It adds 82 tokens to every session and 4,021 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
team-management-receiving-feedback
How to receive code review as technical evaluation rather than social performance — verify claims against the codebase before implementing, push back with evidence, and drop the performative agreement. Use when responding to a human reviewer, a PR comment, or another AI reviewer, and when deciding whether a suggestion…
review
Adversarial design review of a System Design Doc. Interrogates the staff questions, finds the cost-explosion and failure risks, returns a verdict. Sensors and evals gate.
council
Five independent critic subagents in parallel on an idea, plan, design, R&R strategy, grant, or SKILL.md, then a synthesis pass that ranks findings by how much of the argument rests on them, never by vote count. A markdown work plan gets the plan roster (assumptions, pre-mortem, what to delete, alternatives per piece…
pr-reviewer
Review pull requests with full context. Fetches linked Jira tickets, Figma designs, and Notion docs via MCP, spawns parallel subagents for systematic code review (correctness, security, tests, SOLID, clean code), then drafts friendly, humanized GitHub-ready comments. Use when reviewing PRs, examining code changes, or…
implementation-review
Pre-commit quality gate. Invoke before every git commit, after /flagrare:staleness-audit. Seven checks, plan gaps, use-case coverage gaps, missing test scenarios, test philosophy violations (Kent Dodds Testing Trophy), SOLID violations, Clean Code violations, and security vulnerabilities. Each check is delegated to a…
security-audit
Focused security review of a change. Finds HIGH-CONFIDENCE, concretely exploitable vulnerabilities in the staged diff (injection, broken authn/authz, secrets and data exposure, unsafe deserialization, crypto misuse, SSRF) and audits dependencies when a lockfile moved, using the repo's own package manager. Runs as…