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 challengegit 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/challenge)<a href="https://agentmods.dev/skills/thkt/dotclaude/challenge"><img src="https://agentmods.dev/badge/skills/thkt/dotclaude/challenge/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/challenge"><img src="https://agentmods.dev/badge/skills/thkt/dotclaude/challenge.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 | $0.00204 | $0.01758 |
| Opus 5.5 | $0.00082 | $0.00703 |
| Sonnet 5.5 | $0.00041 | $0.00352 |
| Haiku 4.5 | $0.00020 | $0.00176 |
Grade A, and why
challenge 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/challenge - 提案の GO / NO-GO 判定
提案を 2 フェーズで判定し、次の意思決定を検証済みの GO/NO-GO から始めさせる。
入力
$ARGUMENTS に対象を受け取る。提案のファイルパスか、記述そのものを渡す。空なら停止して対象の指定をユーザーに求め、会話から推測しない。複数行のときは先頭行が対象のタイトル。
Phase 1: Grill
提案を証拠で検証し、決着しなかった論点だけをユーザーへ返す。
Step 1: 論点を証拠で決着させる
判断はすべて下表が定める。advisor の自信度では決めない。
| 対象 | 条件 | 満たすときの扱い | 満たさないときの扱い |
|---|---|---|---|
| 論点 | 証拠で答えが 1 つに決まる。優先順位やスコープのように選択が要るものは決まらない | subagent が並列で答えを確かめる | 検証せず未決へ回す |
| 確かめた事実 | 狙う状態が既に成立している、または提案と矛盾する。advisor の見解だけでは満たさない | Phase 2 を飛ばし、根拠を Why に据える | 食い違わなかった主張で続ける |
| 未決の論点 | 後戻りできない、または影響が大きい | AskUserQuestion で聞く。上限 7 問 | advisor の仮説を仮定として進め、Why に全件残す |
.claude/OUTCOME.mdを読む。無ければ$ARGUMENTSと会話から outcome を推定し、AskUserQuestion で確認する。Phase 2 の outcome 攻撃がこれを評価軸に使うので、省略せず確定させる- 提案の論点を洗い出し、表に従って振り分ける
- 検証ループを回す。subagent が並列で答えを確かめ、advisor が振り分けを見直して次の証拠を指す
- 証拠を足しても振り分けが変わらなくなったら打ち切る。上限 3 周。決着しなかった論点は未決へ回す
- 確かめた事実を表に当てる。Phase 2 を飛ばす扱いなら、そのまま出力へ抜ける
- 未決の論点へ advisor が仮説、可逆性、影響度を付け、表に従って振り分ける
Step 2: 引き継ぎを作る
Step 1 の発見を下表の形に集約する。Phase 2 はこれだけを入力に取る。
| 項目 | ソース |
|---|---|
| approach | 提案が何をするかの 1 行要約 |
| decisions | 固まったアーキテクチャ水準の判断。用語確認やスコープ細部は除く |
| trade-offs | 表面化したトレードオフ |
| referenced_files | 参照したファイル |
| outcome_ref | .claude/OUTCOME.md のパスと Behavior / Non-goals / Constraints の要約。無ければ Step 1 で確認した outcome |
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 First seen · 85 lines · 204 tokens per session scan A 943f99b91a46
challenge is a skill published in the GitHub repository thkt/dotclaude (12 stars, last pushed 25d ago), licensed MIT. It adds 204 tokens to every session and 1,758 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 2026-08-30.
Other skills, from other repositories
hf-cloud-python-env-setup
Create an isolated Python environment with a compatible Python version and boto3 for SageMaker or AWS automation. Use before executing AWS Python code; do not use for general Python environment setup.
simplify-code
Parallel 4-agent cleanup of recent code changes.
cpp-coding-standards
C++ coding standards based on the C++ Core Guidelines (isocpp.github.io). Use when writing, reviewing, or refactoring C++ code to enforce modern, safe, and idiomatic practices.
content-hash-cache-pattern
Cache expensive file processing results using SHA-256 content hashes — path-independent, auto-invalidating, with service layer separation.
skill-creator
Create new skills (SKILL.md files), modify and improve existing skills, and design skill descriptions for accurate triggering. Use when the user wants to create a new skill from scratch, edit an existing skill, optimize a skill's description, or convert a workflow they just demonstrated into a reusable skill.
code-quality
Agents should invoke this skill for code reviews, linting/formatting setup, maintainability checks, complexity concerns, warning cleanup, coding standards, or quality gates in Rust, TypeScript, Python, shell, and mixed repos.