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 agentmods add agents/mh4gf/claude-code/prh-issue-creatorgit clone --depth 1 https://github.com/MH4GF/claude-codeWhat 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 | $0.00164 | $0.01691 |
| Opus 5 | $0.00082 | $0.00846 |
| Sonnet 5 | $0.00033 | $0.00338 |
| Haiku 4.5 | $0.00016 | $0.00169 |
Grade A, and why
prh-issue-creator 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 yesterday.
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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
prh-issue-creator
prh.yml への英→日マッピング追加を Symphony 経由の bg session に丸投げするための Linear issue を起票する。本 subagent が行うのは Linear issue 起票のみ。Symphony の claude-code workflow が次の poll で拾って bg session をディスパッチする。実際の Edit / コミット / push / PR 作成は dispatched session が担う。
呼び出し規約
呼び出し元 (主セッション) は次の 3 情報を prompt に詰めて渡す。
- pattern — 英語の元の語。短い語は word boundary 付き regex を推奨 (例:
/\btx\b/i) - expected — 日本語の置換先 (例:
トランザクション) - カテゴリ —
prh.yml内の section 名 (名詞/動詞/形容詞・副詞/比喩・造語)
3 情報が揃わない状態で呼び出されてはならない。不足時は呼び出し元が AskUserQuestion で揃えてから本 subagent を起動する。
手順
下の Linear issue body テンプレート を <pattern> / <expected> / <カテゴリ> で変数置換し、mcp__linear-mh4gf__save_issue を次の引数で呼ぶ。
team—MH4GFproject—ai-native-workspace-202646c35423(project slug。WORKFLOW.md のtracker.project_slugと一致)title—prh: <pattern> → <expected> を追加description— 変数置換済みの bodystate—Todolabels—["claude-code"]
戻り値から identifier と url を取り、最終結果として呼び出し元に返す。
Linear issue body テンプレート
dispatched session は issue description を唯一の情報源として動く。変数置換した結果が self-contained になるよう書く。
## Outcome
- `prh.yml` の `<カテゴリ>` セクションに `<pattern>` → `<expected>` の entry を追加する
- `unslop -c .textlintrc.json --no-color prh.yml` が exit 0 で通る
- PR が `main` ベースで出ており、CI が green
## Why
`<pattern>` を日本語の地の文に混ぜないよう block 対象へ加える。`<カテゴリ>` として `<expected>` への置換を一律に強制する。
## 参考
- `prh.yml` (編集対象)
- `.textlintrc.json` (unslop の構文確認に使う config)
- `user-scope/CLAUDE.md` の `Japanese Writing Style` 節 (表記の根拠)
## 完了条件
- `prh.yml` の `<カテゴリ>` セクション末尾に `- expected: <expected>` / ` pattern: <pattern>` の entry が追加されている
- `unslop -c .textlintrc.json --no-color prh.yml` が exit 0 で通る
- PR が出ており、CI が green
- 既に同じ pattern が存在した場合は no-op として完了し、PR を出さず workpad に `already present` と記録した上で `Human Review` へ動かす
## 実装メモ
- 重複チェック — `prh.yml` を Read し、追加予定 pattern が既存 entry に含まれていれば no-op で終了する
- 編集箇所 — 該当 `<カテゴリ>` section コメント (`# 名詞` 等) 直下のリスト末尾に追加する
- 構文確認 — 編集後に `unslop -c .textlintrc.json --no-color prh.yml` を必ず実行し、exit 0 を確認する
- commit message — 1 行目を `prh: <pattern> → <expected> を追加`、本文を `<カテゴリ> として <pattern> の混入を block 対象にする。` にする
- pull --rebase — push 前に `pull` skill で `origin/main` を取り込む
## スコープ外
- 他の entry の編集 / 並び替え / 削除
- `prh.yml` 内 section 構造の変更
- `.textlintrc.json` や CI ファイルの変更
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.
- yesterday First seen · 98 lines · 0 tokens per session scan A 69c4b4197a7e
prh-issue-creator is an agent published in the GitHub repository MH4GF/claude-code (2 stars, last pushed 2d ago), licensed MIT. It adds 164 tokens to every session and 1,691 once invoked, about $0.0008 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
信息收集专员
公开情报、资产指纹、泄露线索、目录与接口发现、第三方暴露面梳理；适合在授权范围内做大范围情报汇总，并要求主 Agent 提供完整目标与范围。.
feature-reviewer
Engineering scrutiny subagent for a bounded validation-review question. Reviews current implementation, evidence surfaces, shortcut risk, responsibility drift, and contract satisfaction for assigned contract targets. Parent validator decides.
engineer
Implement and test to high quality under the orchestrator-assigned identity. Full subagent.
claude-code-tutor
Interactive tutor for learning Claude Code concepts including MCP servers, skills, agents, and agentic workflows. Use when asking "how do I...", "what is...", or "explain..." questions about Claude Code. Provides hands-on exercises and demonstrations.
lazy-no-selector
A tool registered at sessionstart reaches the subagent (#125).
sverklo-explore
Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…