verify-agent-report

verify-agent-report is a command for Claude Code from s977043/river-review. It costs 34 tokens per session (2,207 once invoked), scanned A, original, MIT.

A command for checking whether an agent’s reported branch, pull request, commit, or files actually exist. A pull request is a proposed code change submitted for review.

In plain words
What is it for?
It is for validating reported branches, pull requests, commit IDs, repositories, and important files with repository and command-line checks.
Why use it?
It catches unverified or fabricated completion reports before their results are merged, reviewed, or used as the basis for more work.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md.

Part of the river-review plugin — 139 skills, 18 commands, 5 agents, 3 hooks shipped together

Good fit It is for validating reported branches, pull requests, commit IDs, repositories, and important files with repository and command-line checks.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/s977043/river-review/verify-agent-report
Install

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.

Clone the repo
git clone --depth 1 https://github.com/s977043/river-review

Made for: Claude Code.

Or install river-review, the plugin that ships this one along with the rest of its 139 skills, 18 commands, 5 agents, 3 hooks.

Wrote 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.

agentmods badge for verify-agent-report

README.md
[![agentmods](https://agentmods.dev/badge/commands/s977043/river-review/verify-agent-report/github.svg)](https://agentmods.dev/commands/s977043/river-review/verify-agent-report)
Your own site
<a href="https://agentmods.dev/commands/s977043/river-review/verify-agent-report"><img src="https://agentmods.dev/badge/commands/s977043/river-review/verify-agent-report/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.

agentmods 80×15 button for verify-agent-report

Your own site · 80×15
<a href="https://agentmods.dev/commands/s977043/river-review/verify-agent-report"><img src="https://agentmods.dev/badge/commands/s977043/river-review/verify-agent-report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,207 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00034 $0.02207
Opus 5.5 $0.00014 $0.00883
Sonnet 5.5 $0.00007 $0.00441
Haiku 4.5 $0.00003 $0.00221

Measured 12d ago against content hash a0994a6e14b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

verify-agent-report 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 12d 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.

.claude/commands/verify-agent-report.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

エージェント完了報告の検証: 「$ARGUMENTS」で報告された branch / PR / commit / ファイルが実在するか、親セッション側のコマンド実行で裏取りする。

このスキルは background 実装エージェントの完了報告を受け取った直後、その成果を merge・レビュー・次タスクの前提として採用する前に呼び出すことを想定している。報告の文面がどれほど具体的でも(PR 番号・テスト件数・コマンド出力ブロック付きでも)、報告品質は実行の証拠にならない。全項目を実コマンドで検証して判定まで行う。

前提

以下のシグナルがあれば /verify-agent-report を先に実行する:

  • background 実装エージェントから「PR 作成済み」「commit 済み」「テスト green」の完了報告を受けた
  • エージェント報告の branch / PR 番号を使って merge・rebase・レビューを始めようとしている
  • 報告に「実コマンド出力」ブロックが含まれている(これも捏造され得る — 2026-07-02 セッションで 4 回観測)

read-only の調査・レビューエージェントの報告はこの failure mode を示していないため対象外。ただし成果物 (branch / PR / ファイル) を伴う報告は常に対象とする。

検証手順

報告から branch 名・PR 番号・commit SHA・主要ファイルを抽出し、以下を順に実行する。

Step 0. script で Step 1〜4 を一括実行する

scripts/verify-agent-report.sh [--worktree <path>] <branch> [PR|-] [SHA|-] [files...]

Step 1〜4 を実行し、項目ごとの PASS / FAIL 表と VERDICT を出す。exit 0 は PASS、exit 1 は FABRICATION_SUSPECTED、exit 64 は引数誤りを表す。PR の読み取り失敗は gh アカウントの切り替わりでも起こるため、FAIL が pr 行だけなら gh api user --jq .login を確認してから再実行する。script が使えない場合は以下の Step 1〜4 を手で実行する。Step 5 は script の対象外である。

WARN は FABRICATION_SUSPECTED に数えない。報告された SHA が branch / PR の先端ではないが、先端の祖先である場合に branch-head と pr 行が WARN tip advanced になる。bot の dist push などで先端が進んだ状態で、commit 行が PASS なら報告は実在する。SHA が branch に無い場合は従来どおり FAIL である。SHA は大文字でも受け付ける。git fetch が失敗すると commit 行が FAIL になり、祖先関係とファイルは未確認のまま残る。

Step 1. branch の実在確認

git ls-remote --exit-code --heads origin refs/heads/<branch>

重要: --exit-code を必ず付ける。素の git ls-remote は ref が存在しなくても空出力で exit 0 を返すため、&& 連鎖では不在を検出できない。exit 2 なら branch は存在しない → 即 FABRICATION_SUSPECTED。

Step 2. PR の実在と head SHA の一致確認 (PR 番号が報告されている場合)

gh pr view <N> --json url,state,headRefOid
  • PR が 404 → 捏造疑い
  • headRefOid が報告された commit SHA と一致するか確認(先頭 7 桁の前方一致で可)
  • url のリポジトリが作業対象リポジトリと一致するか確認(別リポジトリの実在 PR 番号を流用する捏造パターンがある)

Step 3. commit SHA の branch 上の実在確認

git fetch origin <branch> && git log --oneline -5 FETCH_HEAD

報告された commit SHA が出力に含まれるか目視確認。含まれない場合は git log --oneline -20 FETCH_HEAD まで広げてから判定する。

Read the full file on GitHub · 115 lines

Changes

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.

  1. 12d ago Changed · +10 lines a0994a6e14b1
  2. 1mo ago First seen · 105 lines · 34 tokens per session scan A 8e1a0d21b4af

Subscribe to this mod's changes

verify-agent-report is a command published in the GitHub repository s977043/river-review (7 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 2,207 once invoked, about $0.0001 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.