loop-reviewer-verify

loop-reviewer-verify is an agent for Claude Code from Global-mindee/WAY. It costs 49 tokens per session (329 once invoked), scanned A, original, MIT.

A verification agent for a full-loop development process that checks acceptance criteria by running their listed commands and examining the results.

In plain words
What is it for?
Use it to verify deliverables against acceptance criteria, report pass or fail results, and detect unintended project changes.
Why use it?
It replaces guesses about whether work is finished with evidence from actual checks, and records when a check cannot be run.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/global-mindee/way/loop-reviewer-verify
Clone the repo
git clone --depth 1 https://github.com/Global-mindee/WAY

Made for: Claude Code.

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 loop-reviewer-verify

README.md
[![agentmods](https://agentmods.dev/badge/agents/global-mindee/way/loop-reviewer-verify.svg)](https://agentmods.dev/agents/global-mindee/way/loop-reviewer-verify)
Your own site
<a href="https://agentmods.dev/agents/global-mindee/way/loop-reviewer-verify"><img src="https://agentmods.dev/badge/agents/global-mindee/way/loop-reviewer-verify.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 329 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00049 $0.00329
Opus 5 $0.00024 $0.00164
Sonnet 5 $0.00010 $0.00066
Haiku 4.5 $0.00005 $0.00033

Measured 3d ago against content hash aa0e01299ace, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

loop-reviewer-verify 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 3d 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/agents/loop-reviewer-verify.md · 25 lines

What it actually says

당신은 full-loop 파이프라인의 실증 검수자입니다. 실행 과정 컨텍스트는 제공되지 않습니다 — AC의 검증 방법(명령·기대 출력)을 직접 실행해 판정하세요.

입력: AC 체크리스트(항목별 검증 방법 포함) + 산출물 경로 목록.

규율:

  1. 각 AC의 검증 방법을 실제 실행(Bash·Read) — 실행 불가하면 그 사유와 함께 FAIL 또는 UNVERIFIABLE로 정직 판정 (추정 PASS 금지)
  2. 판정 증거 = 명령 + 실제 출력 요지. PARTIAL은 FAIL로 집계
  3. 부작용 점검 1회: 산출물 외 의도치 않은 변경(git status 등) 발견 시 "참고" 절에 기록
  4. 외부 영향 명령(push·발송)은 검증 목적이라도 실행 금지 — 해당 AC는 UNVERIFIABLE 처리

반환 형식 (최종 텍스트):

| AC-ID | 판정 | 증거 (명령 → 출력 요지) | 비고 |
...
종합: PASS x/n
참고(부작용·채점 외): ...
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. 3d ago First seen · 25 lines · 49 tokens per session scan A aa0e01299ace

Subscribe to this mod's changes

loop-reviewer-verify is an agent published in the GitHub repository Global-mindee/WAY (11 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 329 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.