Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/thkt/dotclaudenpx agentmods add skills/thkt/dotclaude/ablateWrote 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/ablate)<a href="https://agentmods.dev/skills/thkt/dotclaude/ablate"><img src="https://agentmods.dev/badge/skills/thkt/dotclaude/ablate/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/ablate"><img src="https://agentmods.dev/badge/skills/thkt/dotclaude/ablate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 6 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00057 | $0.01220 |
| Opus 5.5 | $0.00023 | $0.00488 |
| Sonnet 5.5 | $0.00011 | $0.00244 |
| Haiku 4.5 | $0.00006 | $0.00122 |
Grade A, and why
ablate 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ablate - ハーネスの片側アブレーション
Input
$ARGUMENTS は測定対象を 1 つに絞る要素のパス。省略したときは Phase 1 が列挙した全要素を対象にする。
判定と閾値の所在
アームの一覧、1 アームあたりの実行回数、通過閾値はすべて ${CLAUDE_SKILL_DIR}/scripts/arms.ts の定数が持つ。分類の基準は ${CLAUDE_SKILL_DIR}/scripts/verdict.ts が持つ。DR ゲートの基準、未達の記録を表す印、記録を読む先は ${CLAUDE_SKILL_DIR}/scripts/dr_gate.ts が持つ。計測窓と rare-by-design の集合は ${CLAUDE_SKILL_DIR}/scripts/usage_counts.ts が持つ。規則ごとの起動タスクと固定タスクセットは ${CLAUDE_SKILL_DIR}/references/measurement-criteria.md が持つ。この本文に数値を書き写さない (docs/wiki/deterministic-script-judgment.md)。
Phase 1: 列挙
skills/_lib/harness_elements.ts の enumerate_elements(root) を呼び、ハーネス要素とその分類を得る。$ARGUMENTS が要素のパスを指すときは、その 1 件だけを Phase 2 へ渡す。
node skills/_lib/harness_elements.ts .
Phase 2: アーム実行
Phase 1 が返した要素それぞれについて、arms.ARMS の各アームで arms.arm_command(arm, element) が返す命令を組み、arms.RUN_COUNT 回実行する。その要素の起動タスクは ${CLAUDE_SKILL_DIR}/references/measurement-criteria.md から取る。各 run の結果から、その要素についての観測 1 件を組む。
| 状況 | 扱い |
|---|---|
run 数が arms.RUN_COUNT に届かない |
arms.measurement_status(runs) が unmeasured を返すまま進める |
wiped+1 に渡す要素が決まらない |
arm_command が ValueError で止まるので、要素を確定してから呼ぶ |
| 実行が失敗し結果を読めない run がある | その run を数えず、observation に届いた run 数だけを載せる |
Phase 3: レポート
report.write_report(root, observations) を呼ぶ。削除候補がレポートへ届く前に dr_gate.gate が docs/decisions/ を読み、生きている記録が支配する要素を保留するので、Summary はその件数を分けて数える。同時に usage_counts.ts も実行し、各要素の発火回数と最終使用日を同じ Harness Elements 表へ組み込む。見る経路は 1 つで、別経路を並走させない。書き出し先の既定は docs/audit/ で、ファイル名は UTC の <YYYY-MM-DD>-<HHMMSS>-ablate.md。節の順は ${CLAUDE_SKILL_DIR}/templates/report-template.md が持つ。
node --input-type=module -e 'const { write_report } = await import("./skills/ablate/scripts/report.ts"); let data = ""; for await (const chunk of process.stdin) data += chunk; console.log(write_report(".", JSON.parse(data)));' < <observations.json>
What ships with it
12 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.
- references/measurement-criteria.md 9.0 KB
- scripts/arms.ts 4.7 KB runs code
- scripts/dr_gate.ts 4.0 KB runs code
- scripts/enforcer_map.ts 6.6 KB runs code
- scripts/exposure.ts 7.2 KB runs code
- scripts/reference_arm.ts 11 KB runs code
- scripts/reference_match.ts 5.5 KB runs code
- scripts/reference_observation.ts 5.6 KB runs code
- scripts/report.ts 13 KB runs code
- scripts/usage_counts.ts 12 KB runs code
- scripts/verdict.ts 2.8 KB runs code
- templates/report-template.md 989 B
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 dbbed96e4fd3
- 1mo ago First seen · 56 lines · 57 tokens per session scan A 80c56b17feb3
ablate is a skill published in the GitHub repository thkt/dotclaude (12 stars, last pushed 25d ago), licensed MIT. It adds 57 tokens to every session and 1,220 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 2026-08-30.
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…