Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/s977043/river-reviewnpx agentmods add commands/s977043/river-review/release-kickWrote 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/commands/s977043/river-review/release-kick)<a href="https://agentmods.dev/commands/s977043/river-review/release-kick"><img src="https://agentmods.dev/badge/commands/s977043/river-review/release-kick/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/commands/s977043/river-review/release-kick"><img src="https://agentmods.dev/badge/commands/s977043/river-review/release-kick.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 | $0.00064 | $0.03767 |
| Opus 5.5 | $0.00026 | $0.01507 |
| Sonnet 5.5 | $0.00013 | $0.00753 |
| Haiku 4.5 | $0.00006 | $0.00377 |
Grade A, and why
release-kick scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
release PR #$ARGUMENTS を、BLOCKED 解除からマージ・リリース公開の検証まで一貫して実行する。
release-please が生成するリリース PR の head は GITHUB_TOKEN push であるため、通常は mergeStateStatus: BLOCKED("N of N required checks are expected")になる(CLAUDE.md「N of N required checks are expected = bot/GITHUB_TOKEN push」ガード参照)。この BLOCKED の原因は docs/runbook/bot-pushed-head-kick.md が SSoT。kick の正規手順は scripts/release-please-kick.sh である(workflow_dispatch 版は #2709 で削除。経緯は #1807)。本コマンドはそれを前提に、実際にマージして公開を確認するまでの実行手順を1コマンド化したもの。矛盾があれば runbook を正とし、本コマンドを修正する。
手順
Step 0. 手順書の鮮度確認
git fetch origin
git diff --quiet HEAD origin/main -- .claude/commands/release-kick.md docs/runbook/bot-pushed-head-kick.md || echo "手順書が古い: origin/main 版を読み直すこと"
ローカル main が origin より遅れていると、改訂前の手順書を読んだまま実走することになる。上のメッセージが出たら git pull で追いついてから、本コマンドと runbook を読み直す。差分がなければ何も出力されない。
v1.67.1 の実走では、ローカルが 24 コミット遅れていた。その結果、#1702 による改訂前の版を読み込んだまま実走している。#1702 のマージ時刻はキックの 16 分前だった。
Step 1. gh アカウント確認
gh api user --jq .login | grep -q s977043 || gh auth switch -u s977043
PreToolUse hook (gh-account-guard.sh) が defense-in-depth で効くが、セッション開始時の確認は省略しない。
s977043 は本リポジトリのメンテナアカウント(CLAUDE.md「Verify gh active account before write ops」ガードと同一の値で、そちらが SSoT)。フォーク運用時は自分のアカウントに読み替える。
Step 2. PR 状態の確認と BEHIND 判定
gh pr view $ARGUMENTS --json state,mergeStateStatus,headRefOid
releaseBranch=$(gh pr view $ARGUMENTS --json headRefName --jq .headRefName)
gh api "repos/:owner/:repo/compare/main...$releaseBranch" --jq '{status, ahead_by, behind_by}'
mergeStateStatus: BLOCKED は release-please PR の通常挙動。CLEAN なら Step 3〜5 をスキップして Step 6 へ進む。
BLOCKED の場合は behind_by の値で次に打つ手が変わる。mergeable_state は単一の値しか返さず BEHIND と BLOCKED の複合状態を見分けられないため、compare の behind_by で判定する。
behind_by |
状態 | 次に進む Step | 空コミット kick |
|---|---|---|---|
> 0 |
BEHIND + BLOCKED | Step 3(update-branch) | CI が実発火すれば不要 |
0 |
純 BLOCKED | Step 4(kick) | 必要 |
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.
- 5d ago Changed ccff7c39f21a
- 6d ago Changed 08614eb079f4
- 1mo ago Changed · +10 lines 7a6c50fddd16
- 1mo ago Changed 90cba73af0c2
- 1mo ago First seen · 148 lines · 64 tokens per session scan A 2010d95aad41
release-kick is a command published in the GitHub repository s977043/river-review (7 stars, last pushed today), licensed MIT. It adds 64 tokens to every session and 3,767 once invoked, about $0.0003 per session on Opus 5.5. 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 commands, from other repositories
release
Release manager for frontend and mobile. Writes App Store notes, user-facing changelog, flags stale docs and landing copy. Actions: notes | changelog | docs | sync.
ia-document-release
Post-ship documentation sync. Reads all project docs, cross-references the diff, updates README/ARCHITECTURE/CONTRIBUTING/CLAUDE.md to match what shipped, polishes CHANGELOG voice, and optionally bumps the version.
ia-changelog
Create engaging changelogs for recent merges to main branch.
release
Bump version, commit, push, mirror to ai-skills, and update local plugin.
ship
Branch, commit, open PR, gather Claude + every enabled AI reviewer (Copilot, CodeRabbit, etc.), fix/justify/resolve every finding, loop until clean, then merge. Run only when implementation is finished AND the owner has said to ship (e.g. "ship it") — never self-invoke just because the work looks done. To design and…
brief
Brief a PR, MR or the current branch with Punchcard — the reviewer's orientation before the review, never a review.