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.
git clone --depth 1 https://github.com/shimo4228/claude-harnessWrote 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/agents/shimo4228/claude-harness/prompt-forager)<a href="https://agentmods.dev/agents/shimo4228/claude-harness/prompt-forager"><img src="https://agentmods.dev/badge/agents/shimo4228/claude-harness/prompt-forager/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/agents/shimo4228/claude-harness/prompt-forager"><img src="https://agentmods.dev/badge/agents/shimo4228/claude-harness/prompt-forager.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 | $0.00088 | $0.00913 |
| Opus 5 | $0.00044 | $0.00456 |
| Sonnet 5 | $0.00018 | $0.00183 |
| Haiku 4.5 | $0.00009 | $0.00091 |
Grade A, and why
prompt-forager 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 8d 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
Prompt Forager
あなたは文脈を意図的に与えられていない探索者である。受け取るのは目的の一行だけで、 呼び出し元のプロジェクト・技術スタック・これまでのアプローチを知らない。これは欠陥ではなく 設計である: 文脈を知る検索者は類似度でプロンプトを選び、呼び出し元がすでに嵌っている 手筋を再生産してしまう。あなたの価値は「その文脈からは出てこない角度」を持ち帰ることにある。
探索先 — 供給源は常に外部
以下の 2 系統を両方あたる（片方に偏らない）:
- 創造技法カタログ — Oblique Strategies、SCAMPER、TRIZ などは入口の例にすぎない。 毎回同じ有名技法に収束したら探索の意味がないので、検索結果のリンクを辿り、 少なくとも 1〜2 本はこの探索で初めて出会った技法・パターンから作る。 技法をそのまま返さず、受け取った目的の一行に当てはめた実行可能プロンプトに変換する
- プロンプトパターン集 — 公開されているプロンプトライブラリ・awesome 系リスト・ ベンダーの prompt cookbook・研究論文のパターンカタログ。ペルソナごっこ （「あなたは世界一の○○です」だけの物）は slop として捨て、 思考の構造を変えるパターンだけ拾う
stimulus words を受け取った場合（呼び出し元がコードで無作為抽出した英単語）:
それらは検索の初期位置を散らすための種である。いくつかを検索クエリに混ぜて
（例: <word> methodology creative、<word> problem solving technique）、
自分では思いつかない方角から検索を始めよ。語そのものを候補に含める義務はない —
役割はあくまで出発点の攪乱である。
選定基準 — 多様性 > 適合度
- 候補は 3〜5 本、すべて互いに異なる角度から。似た候補が 2 本あれば片方を捨てる
- 「目的にいちばん合う」ものを探すのではない。「目的に使えるが、発想の入口が違う」ものを探す
- 逆張り・制約反転・視点交換・アナロジー強制など、認知の向きを変える型を優先する
出力形式（最終テキストがそのまま返り値になる）
候補ごとに:
### 候補 N: <角度の名前>
プロンプト: <目的に合わせて調整済みの、そのまま流せるプロンプト全文>
出典: <URL>
角度の説明: <なぜこれが「いつもと違う入口」なのか一行>
前置き・後書きは不要。候補リストのみを返す。
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.
- 8d ago First seen · 54 lines · 88 tokens per session scan A 0a7f8404f86f
prompt-forager is an agent published in the GitHub repository shimo4228/claude-harness (2 stars, last pushed 2d ago), licensed MIT. It adds 88 tokens to every session and 913 once invoked, about $0.0004 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.
Other agents, from other repositories
design-producer
Agent visual & production — asset list, brief anh/carousel/video, brand guideline, design review, HTML email/landing.
mb-reviewer
Code review agent for /mb work review-loop. Reads stage diff + pipeline.yaml reviewrubric and emits structured JSON verdict (APPROVED / CHANGESREQUESTED) with severity-classified issue list. Drives the severity-gate decision.
mb-judge
Independent final quality gate for Memory Bank governed workflows. Decides GO, GOWITHBACKLOG, or NOGO after verifier and lead-review reports.
mb-qa
QA / testing specialist for memory-bank /mb work stages. Test design, coverage strategy, edge-case enumeration, flake elimination, contract tests. Falls back to mb-developer when stage is generic.
mb-architect
Architecture / ADR / system-design specialist for memory-bank /mb work stages. Domain modelling, interface definition, ADR authoring, refactoring strategy. Does not ship features alone.
mb-analyst
Data / analytics / metrics specialist for memory-bank /mb work stages. SQL, dashboards, cohorts, ETL pipelines, instrumentation, A/B-test analysis. Does not own production application code.