Borrowing it
Nothing to install: this file belongs to Global-mindee/WAY. 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/Global-mindee/WAY/main/.claude/agents/loop-reviewer-verify.mdgit clone --depth 1 https://github.com/Global-mindee/WAYWrote 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/global-mindee/way/loop-reviewer-verify)<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/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/agents/global-mindee/way/loop-reviewer-verify"><img src="https://agentmods.dev/badge/agents/global-mindee/way/loop-reviewer-verify.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 | $0.00049 | $0.00329 |
| Opus 5.5 | $0.00020 | $0.00132 |
| Sonnet 5.5 | $0.00010 | $0.00066 |
| Haiku 4.5 | $0.00005 | $0.00033 |
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 1mo 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.
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:
- 각 AC의 검증 방법을 실제 실행(Bash·Read) — 실행 불가하면 그 사유와 함께 FAIL 또는 UNVERIFIABLE로 정직 판정 (추정 PASS 금지)
- 판정 증거 = 명령 + 실제 출력 요지. PARTIAL은 FAIL로 집계
- 부작용 점검 1회: 산출물 외 의도치 않은 변경(git status 등) 발견 시 "참고" 절에 기록
- 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): ...
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.
- 1mo ago Changed aa56bc0efbe5
- 1mo ago First seen · 25 lines · 49 tokens per session scan A aa0e01299ace
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 5.5. 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
Haiku
Anthropic-family cheap worker named for the model it runs — the haiku alias (resolved from CURRENT.haiku in models.ts, never pinned in prose), in-process on the subscription, no codex. Carries the low rung, at high effort (2026-10-07, in place of the Terra and Luna codex workers): near-mechanical work a script could…
test-designer
USE THIS for independent test case generation during /run (PAIRMODE). Designs tests from AC and seed spec only — never reads implementation code. Prevents biased testing. Based on AgentCoder (2024) test separation methodology. MUST be spawned with isolation worktree to physically prevent source code access.
evaluator
USE THIS WHEN verifying implementation against a seed spec, running gates, or assessing AC compliance. ALWAYS invoke during /evaluate. Never fixes — only judges Pass/Fail with file:line evidence. Runs 3-stage verification (Mechanical → Semantic → Judgment).
cli-test-automation
Automate CLI application testing workflows using byobu sessions with comprehensive verification, error handling, and reporting. Perfect for testing command-line tools, plugins, and terminal applications with consistent methodologies and detailed test result analysis.
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
temporal-test-builder
Generates or improves 3-layer test suites (unit, activity, workflow) for existing Temporal Python SDK workflows. Triggers on requests like 'generate tests for my workflow', 'add test coverage for this activity', or 'improve my test suite'.