prompt-perturb

prompt-perturb is a skill for Claude Code from shimo4228/claude-harness. It costs 194 tokens per session (1,040 once invoked), scanned A, original, MIT.

An idea-generation tool that fetches creative prompts from outside sources after removing project-specific context from the search.

In plain words
What is it for?
Use it to introduce a different angle into feature brainstorming or other open-ended creative work, then apply the selected prompt to the real project.
Why use it?
It helps when brainstorming has become repetitive or stuck on familiar approaches. It is not intended to find the best or correct solution.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Good fit Use it to introduce a different angle into feature brainstorming or other open-ended creative work, then apply the selected prompt to the real project.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/shimo4228/claude-harness/prompt-perturb
Install

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.

Any agent
npx skills add shimo4228/claude-harness --skill prompt-perturb
Clone the repo
git clone --depth 1 https://github.com/shimo4228/claude-harness

Made for: Claude Code.

Wrote 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.

agentmods badge for prompt-perturb

README.md
[![agentmods](https://agentmods.dev/badge/skills/shimo4228/claude-harness/prompt-perturb/github.svg)](https://agentmods.dev/skills/shimo4228/claude-harness/prompt-perturb)
Your own site
<a href="https://agentmods.dev/skills/shimo4228/claude-harness/prompt-perturb"><img src="https://agentmods.dev/badge/skills/shimo4228/claude-harness/prompt-perturb/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.

agentmods 80×15 button for prompt-perturb

Your own site · 80×15
<a href="https://agentmods.dev/skills/shimo4228/claude-harness/prompt-perturb"><img src="https://agentmods.dev/badge/skills/shimo4228/claude-harness/prompt-perturb.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 194 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,040 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00194 $0.01040
Opus 5 $0.00097 $0.00520
Sonnet 5 $0.00039 $0.00208
Haiku 4.5 $0.00019 $0.00104

Measured 12d ago against content hash b9810c1d2ba1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

prompt-perturb 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/draw.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/prompt-perturb/SKILL.md · 53 lines

What it actually says

Prompt Perturb — 文脈遮断プロンプト注入

作業が局所解に嵌るのは、生成もレビューも同じ文脈分布から出てくるからである。 この skill は検索者を文脈から遮断することで分布の外からプロンプトを引く。 repo の中から「目的に合うプロンプト」を探すと類似度選択でいつもの手筋が再生産される — だから検索者には目的の一行だけを渡す。遮断が甘いほど効果が消える。

手順

1. 目的を一行に蒸留する(遮断ステップ)

いまの作業の目的を、プロジェクト名・技術スタック・制約・これまでのアプローチを すべて落として一行にする。固有名詞が残っていたら抽象化する (例: 「pdf2anki の Phase 4 機能案出し」→「学習素材の変換ツールの新機能を発想したい」)。

ここで文脈を足したくなるのが最大の罠。合いすぎる候補が返ってきたら遮断失敗のサイン。

2. 乱数種を引き、prompt-forager を起動する

まず bash <この skill のディレクトリ>/scripts/draw.sh を実行する。出力はシステム辞書から 無作為抽出した刺激語で、forager の外部検索の初期位置を散らすための種である (LLM に「ランダムに」と頼むと自分の分布から選ぶため、抽選はコードが持つ。 ローカルに技法リストやカードデッキは置かない — 閉じた札はそこに収束するため、 選択肢の供給源は常に外部の検索結果とする)。

Agent ツールで prompt-forager を起動し、蒸留した一行 + draw.sh の出力のみを渡す。 会話履歴の要約・補足説明を付けない。

3. 候補を原文のまま提示する

返ってきた 3〜5 候補を要約せず原文のまま提示し、ユーザーに選んでもらう。 「おまかせ」と言われたら、現在のセッションでまだ使っていない認知の向き (逆張り・制約反転・視点交換・アナロジー)に最も遠い候補を選び、選定理由を一行添える。

4. 選ばれたプロンプトを現在の文脈で実行する

ここで初めてプロジェクト文脈と合流する。プロンプトの指示に素直に従い、 早すぎる「現実的には…」の絞り込みで摂動を殺さない — 収束は摂動の後でよい。

使用上の注意

  • 1 回の行き詰まりにつき 1 引きまで。連発すると探索が物色に変わる(iteration bound)
  • 摂動の成果はすぐ判定しない。異角度プロンプトの価値はその場の出力でなく、 数手先で「あの角度がなければ出なかった」形で現れることが多い
Files

What ships with it

1 file 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.

Changes

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.

  1. 12d ago First seen · 53 lines · 194 tokens per session scan A b9810c1d2ba1

Subscribe to this mod's changes

prompt-perturb is a skill published in the GitHub repository shimo4228/claude-harness (3 stars, last pushed 6d ago), licensed MIT. It adds 194 tokens to every session and 1,040 once invoked, about $0.0010 per session on Opus 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 2026-08-31.