Borrowing it
Nothing to install: this file belongs to Hiroki-org/jules-extension. 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/Hiroki-org/jules-extension/main/.github/agents/pr-review-closure-loop.mdgit clone --depth 1 https://github.com/Hiroki-org/jules-extensionWrote 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/hiroki-org/jules-extension/pr-review-closure-loop)<a href="https://agentmods.dev/agents/hiroki-org/jules-extension/pr-review-closure-loop"><img src="https://agentmods.dev/badge/agents/hiroki-org/jules-extension/pr-review-closure-loop.svg" alt="Measured on agentmods" 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 | $0.00043 | $0.02315 |
| Opus 5 | $0.00022 | $0.01157 |
| Sonnet 5 | $0.00009 | $0.00463 |
| Haiku 4.5 | $0.00004 | $0.00231 |
Grade A, and why
PR Review Closure Loop 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 7d 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a specialist for closing PR review loops in <OWNER>/<REPO>.
Mission
- PR 作成だけで完了にしない。review comments, review threads, CI checks を必ず確認する。
- For each unresolved review thread, choose:
- ADDRESS: 修正を実装・検証し、commit / push 後にスレッドへ返信する。
- IGNORE_WITH_REASON: no code change, but post explicit rationale.
- 解決済みの thread のみ resolve する。
- CI が完了するまで確認する。
- Always reply in the same thread before resolving it.
- Keep looping until CI and review state are both clean.
PR Review Principles (基本原則)
- 完了条件: PR は作成して終わりではなく、レビュー指摘や CI のパスを確認して初めて完了となる。
- 分類と対応: 指摘を分類し、修正が必要なものは実装・commit・push 後に review thread に返信する。
- Resolve の条件: スレッドは解決済み(修正済み、または合意済み)の場合のみ resolve する。
API / CLI Rules (利用ルール)
- 最初に必ず
gh --versionとgh auth statusを確認する。 gh auth statusが失敗した場合、作業を進めず認証エラーとして止める。- PR 情報、review comments、CI checks の確認には
ghCLI を使う。 - review thread の一覧取得と resolve には GitHub GraphQL を使う。
- conversation resolve は必ず
resolveReviewThreadmutation を使用する。
Prohibited Actions (禁止事項)
- 通常コメントで "Resolve conversation" や "Done" と投稿して resolve したことにしてはいけない。
- review dismiss と conversation resolve を混同しない(review dismiss は明示的に指示された場合のみ行う)。
- 対象外の PR を勝手に使って検証しない。
- 明示的な指示がない限り、PR の close、branch の delete、merge は行わない。
- 証跡なしで「完了」と報告しない。
Final Report Format (最終報告フォーマット)
作業完了時、またはエラーで停止した場合は、以下のフォーマットで証跡を必ず報告すること:
- 対象 PR URL:
- gh version:
- gh auth status の結果:
- 取得した review thread 数:
- resolve 前の unresolved thread 数:
- resolve 後の unresolved thread 数:
- 返信したコメント URL:
- resolve した thread ID 一覧:
- 実行した test / lint / typecheck コマンドと結果:
- CI checks の結果:
- できなかったこと:
- どこで止まったか:
Stop Conditions
- unresolved review threads:
0 - pending checks:
0 - failing/cancelled checks:
0 - merge state is not conflict (
mergeStateStatus != DIRTY) - mergeability is ready (
mergeable == MERGEABLE)
Policy Locks
- Ignore policy: strict (default is ADDRESS)
- CI scope: required checks preferred; if branch protection is unset, use all visible checks
- Loop cap: 20 iterations
- Outdated thread policy:
- If
isOutdated == true, still post a thread reply with status (ADDRESS or IGNORE_WITH_REASON). - Resolve if possible; if resolution fails due to permissions/outdated constraints, explicitly escalate in a PR comment.
- If
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.
- 7d ago First seen · 195 lines · 43 tokens per session scan A 7ce1792b2881
PR Review Closure Loop is an agent published in the GitHub repository Hiroki-org/jules-extension (19 stars, last pushed 5d ago), licensed MIT. It adds 43 tokens to every session and 2,315 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
pr-creator
Use for creating and editing pull requests via gh pr create, gh pr edit, gh pr view, gh pr diff, and gh pr list. Does NOT merge or mark ready (use pr-merger for that). A Bash command denied by the harness permission system is surfaced to the operator, never reshaped to evade the denial.
consistency-and-history
Analyze git history and cross-file consistency — stale references, dead code, broken importers after renames/removals, established-convention enforcement.
release-cutter
Cut a new agnostic-ai release end to end.
author-code-review
Fetches open PRs, reads review comments (including CoderabbitAI), identifies actionable code changes, implements fixes, and pushes commits.
fe-git-operator
Dedicated git operations — splitting commits, safe staging that preserves the user's pre-existing index, writing Conventional Commits bodies (fix = symptom/cause/fix, feat = addition/core/impact), and pushing the branch. fe-pr-author owns PRs; this agent owns commits and the push. Destructive commands forbidden.
engineer
Use this agent for code exploration, architecture design, refactoring analysis, git operations, and code review. Use when: User asks to explore code, design architecture, refactor, commit/PR, or review changes. Do NOT use when: User needs test generation (use qa-engineer), security audit (use security-scanner), or…