Borrowing it
Nothing to install: this file belongs to suisya-systems/claude-org-ja. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/suisya-systems/claude-org-ja/main/.claude/skills/pr-watch-pane/SKILL.mdgit clone --depth 1 https://github.com/suisya-systems/claude-org-jaWrote 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/suisya-systems/claude-org-ja/pr-watch-pane)<a href="https://agentmods.dev/skills/suisya-systems/claude-org-ja/pr-watch-pane"><img src="https://agentmods.dev/badge/skills/suisya-systems/claude-org-ja/pr-watch-pane/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/suisya-systems/claude-org-ja/pr-watch-pane"><img src="https://agentmods.dev/badge/skills/suisya-systems/claude-org-ja/pr-watch-pane.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, 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 Agent Snooping · line 115 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 531 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 540 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Rogue Agent · line 303 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 303 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00261 | $0.18155 |
| Opus 5 | $0.00130 | $0.09078 |
| Sonnet 5 | $0.00052 | $0.03631 |
| Haiku 4.5 | $0.00026 | $0.01816 |
Grade A, and why
pr-watch-pane 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 11d 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 — 623 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pr-watch-pane: CI / マージ監視を専用ペインで回す
tools/pr-watch.sh <PR> --repo <owner/repo> --merge-watch を broker tmux セッション
内の専用ペイン (name="pr-watch-<PR>") で起動する。Bash tool の background 起動は
session 寿命依存で、CI 監視のような長時間 watcher には不適（公式設計の対象外）。broker
ペイン spawn を経由することで sandbox 外・窓口セッション非依存（/clear や窓口の
context リセットと無関係）に監視が継続し、人間が tmux ペインで直接見えるので可視性も高い
（feedback-dispatcher-visibility 整合）。
監視結果は二経路で残る（どちらも pr_watch.py の既存挙動。本 skill は形を変えない）:
.state/state.dbevents テーブル …ci_completed/pr_merge_watch_timeoutの canonical event 行（payload 形・CI_COMPLETED/PR_MERGED/PR_MERGE_WATCH_TIMEOUTのメッセージ形は不変）。これが判定の canonical 記録。.state/pr-watch-<PR>.log+ tmux スクロールバッファ … 人間可読の生ログ二段。
peer push は best-effort:
pr_watch.pyは CI 確定・マージ時に窓口へCI_COMPLETED/PR_MERGEDの peer message を送ろうとするが、これはtools/peer_notify.py経由の best-effort（broker send CLI 不在 / 解決先 transport が未構成の pane では no-op）。daemon が非既定 state dir（herdr dogfood 等）で動く環境では、pane env にORG_BROKER_STATE_DIRが無いと broker send が既定.state/brokerを掴んで push が欠落する （欠落しても canonical の events DB 行には影響しない）。待つべき正路は上記 events DB 行と 可視ペインであり、push の到達を merge gate の 前提にしない（org-pull-request の CI/merge gate は events DB を一次ソースにする）。
輸送層（transport）両系 — 既定
broker/ opt-inrenga: 本ファイル（および各スキル）の peer message・pane 操作はmcp__org-broker__*で書いてあり、ORG_TRANSPORT無設定＝既定brokerではそのまま従えばよい。ORG_TRANSPORT=renga（opt-in、切戻し可）では MCP サーバー名がrenga-peersになり、完全修飾名がmcp__org-broker__*→mcp__renga-peers__*に機械置換される（引数形・セマンティクスは同一なので操作の論理は変わらない）。輸送依存で手順が変わる差は次の 3 点:
- 受信モデル（既定 = push 一次 =
claude/channel/ pull フォールバック）: 既定 broker は push 一次に設計されている（runtime push-first 0.1.24+、設計 SoT は transport-labdocs/design/broker-native-roles.md§9）: 各ペイン同居の channel sidecar（server:org-broker-channel）が broker キューを ~1 秒間隔で claim→push し、notifications/claude/channelで本文を idle セッションへ注入する（「受けたら即応答」契機が生まれる）。ワーカー ack（to_id="worker-{task_id}"）・retro gate ack（to_id="dispatcher"）・ディスパッチャー handover 経路のsend_message/check_messages/send_keys/inspect_paneは同じツール名（mcp__org-broker__*）で動く。pull はフォールバック層: sidecar 不在 / unhealthy（heartbeat timeout でdelivery_mode=PULL）/ channel 非対応ペイン（codex pull-peer）/ claude.ai login 不在時は、各役割が自身の cadence で能動的にcheck_messagesする（役割別 cadence: worker=ターン境界 / 完了後 bounded/loop・dispatcher=/loop 3m・secretary=ターン冒頭。「ナッジを見たらcheck_messages」prose は撤回せずこの fallback cadence として読む）。ORG_TRANSPORT=renga（opt-in）では、ワーカー報告・ディスパッチャー応答が<channel source="renga-peers" …>として in-band で push される（renga の in-band push と broker push 一次は同じ即応契機）。契約面は Surface 8 + push-primary amendment で push 一次が ratified 済み（2026-06-15、S3。pull は fallback として retain・renga 不変）。- spawn 儀式（既定 = folder-trust 承認 + dev-channel sidecar 承認の 2 段）: 子ペイン起動時、既定 broker は
--mcp-config <broker>を注入し Claude Code の folder-trust プロンプトをsend_keys(enter=true)で機械承認するのに加えて、push 一次のため channel sidecar を--dangerously-load-development-channels server:org-broker-channelで load し dev-channel 承認プロンプト（spawn-flow 3-3b）をsend_keys(enter=true)で機械承認する（folder-trust + dev-channel の 2 段承認。詳細は.dispatcher/references/spawn-flow.md3-2 / 3-3b、設計は broker-native-roles.md §9.5）。ORG_TRANSPORT=renga（opt-in）では--dangerously-load-development-channels server:renga-peersを注入し「Load development channel?」を Enter 承認する 1 段。注: attention watcher は transport 非依存の CLI ペインであり、folder-trust / dev-channel いずれの 2 段承認の対象外（spawn 儀式の反転に巻き込まない）。- エラー分岐（既定 = broker 拡張コード込み）: 既定 broker は shared codes（
pane_not_found/last_pane/invalid-params、Surface 6）に加え broker 固有[token_invalid]/[session_invalid]/[tool_not_authorized]/[no_backend]（= adapter_unavailable）/[nudge_failed]/[peer_not_found]/[name_taken]/[unknown_tool]を返しうる（未知コードは default-branch で escalate）。ORG_TRANSPORT=renga時は broker 固有コードは発生せず shared codes + renga 固有コードのみ。契約面の正本は
docs/contracts/backend-interface-contract.mdSurface 8（broker auth & delivery、ratified 2026-06-14）+ 末尾「Ratified amendment (2026-06-15): push-primary delivery」（S3。broker push 一次が既定の契約、pull は structural fallback として retain）、設計 SoT は transport-labdocs/design/broker-native-roles.md§9（push 一次）/docs/design/ja-migration-plan.md§5・§8。opt-inrengaは削除せず常時有効な fallback として維持する（切戻しの安全装置）。broker 実走（dogfood）は Epic #6 Issue G スコープであり、本ファイルの既定運用経路ではない（既定の二フレーム注記（Refs #604）: ここでの「既定broker」はコード既定フレーム —tools/transport.py: DEFAULT_TRANSPORTが runtime 0.1.28 (Epic #586) でbrokerにフリップ済みで、ja 生成器・transport.resolve()はこのコードフレームで render するため生成面はこう表示する。別に運用既定フレームがあり、broker 実走 dogfood が Epic #6 Issue G まで未活性のため運用上の既定経路はrenga。両フレームは指す対象（コード定数 vs 運用経路）が異なり矛盾しない。総説は rootCLAUDE.md「輸送層（transport）両系」節。）
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.
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.
- 11d ago First seen · 623 lines · 261 tokens per session scan A d986018ddfea
pr-watch-pane is a skill published in the GitHub repository suisya-systems/claude-org-ja (5 stars, last pushed 5d ago), licensed MIT. It adds 261 tokens to every session and 18,155 once invoked, about $0.0013 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 skills, from other repositories
pr-watch
Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.
release-readiness-check
Verify all prerequisites are met before a release by checking PRs, CI/CD status, environment health, and blocking issues across GitHub, ArgoCD, and Jira. Use before cutting a release, deploying to production, or during release planning.
pipe
Designing GitHub Actions workflows in depth: trigger strategy, security hardening, performance optimization, PR automation, and Reusable Workflow design.
gear
Managing dependencies, CI/CD, advanced GitHub Actions workflows, containers, secrets, and operational config. Use for build, workflow, or environment work.
devops-assistant
Assists in version control, deployment, and automation tasks, ensuring smooth DevOps operations and workflow efficiency.
oma-dev-workflow
Use when setting up or optimizing developer workflows in a monorepo, managing mise tasks, git hooks, CI/CD pipelines, database migrations, or release automation. Invoke for development environment setup, build automation, testing workflows, and release coordination.