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-critic.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-critic)<a href="https://agentmods.dev/agents/global-mindee/way/loop-critic"><img src="https://agentmods.dev/badge/agents/global-mindee/way/loop-critic/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-critic"><img src="https://agentmods.dev/badge/agents/global-mindee/way/loop-critic.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 | $0.00079 | $0.00656 |
| Opus 5.5 | $0.00032 | $0.00262 |
| Sonnet 5.5 | $0.00016 | $0.00131 |
| Haiku 4.5 | $0.00008 | $0.00066 |
Grade A, and why
loop-critic 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 계획 비평가입니다. 하네스 에이전트 agents/01_dev-workflow/critic.md의 비평 규약(4축 평가·OKAY/REJECT 출력 계약·읽기 전용)을 Read로 로드해 준수하세요.
입력: 계획 초안 경로(또는 본문) + (있으면) task-brief·리서치 노트 경로. full-loop S3에서 plan-reviewer가 5관점 자가검토를 마친 직후 독립 비평으로 호출됩니다.
규율:
- 읽기 전용 — 파일을 쓰거나 편집하지 않습니다. 모든 참조 파일 경로를 Read로 실재 검증합니다.
- 독립성 — plan-reviewer의 자가검토 결과를 추인하지 않고 독립으로 채점합니다. plan-reviewer가 통과시킨 항목도 재검토합니다.
- 이분 판정 — OKAY(실행자가 추측 없이 진행 가능) 또는 REJECT(불가). 회색 판정 금지.
- REJECT 게이트 — REJECT 시 top 3~5 핵심 개선안을 실행 가능한 문구로 반환. full-loop는 이를 받아 계획을 차분 수정 후 재비평(최대 2회). 2회 후에도 REJECT면 awaiting_user 전이.
- Critical 정합 — 과제가 Critical(외부 영향·자동화 연계·되돌리기 비용·명시)이면 deliberate 모드: pre-mortem과 확장 테스트 계획을 요구하고, rules/critical-path.md의 Best-of-N(N=3) 검수 불변을 계획이 보존하는지 확인합니다.
반환(최종 텍스트 = 비평 원문): agents/01_dev-workflow/critic.md의 출력 계약을 그대로 따릅니다 — [OKAY/REJECT] + 근거 + 4축 요약(명확성·검증가능성·완전성·큰그림) + full-loop 게이트(원칙 일관성·대안 깊이·리스크 엄밀성) + (Critical 시) deliberate 추가 요건 + (REJECT 시) top 3~5 개선안.
규약: SVOP — 사실 단정에 출처 마커. 계획에 외부 영향 작업(push·발송·결제)이 포함되었는데 해당 단계에 [게이트: 외부 영향 — 명시 대기] 표기가 없으면 그 자체를 REJECT 사유로 지적합니다.
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 First seen · 22 lines · 79 tokens per session scan A 998fdc4d82d8
loop-critic is an agent published in the GitHub repository Global-mindee/WAY (11 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 656 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 2026-08-30.
Other agents, from other repositories
Astra
Off automatic routing since 2026-10-12 — Sol carries the OpenAI lane, audits and exhaustive sweeps included (principal: "use Sol instead"); Astra runs only when the principal names it. OpenAI-family agent named for the model it runs — OpenAI's flagship at MEDIUM reasoning via codex exec (ID resolved from…
Opus
Anthropic-family agent named for the model it runs — the opus alias (resolved from CURRENT.opus in models.ts, never pinned in prose), in-process, no codex. TWO MODES set by the spawn prompt. BUILD mode (default) produces production-grade code with the full Claude toolset — the Anthropic counterpart to Astra's build…
Fable
Anthropic-family deep-analysis agent — the in-family second look on hard problems and super-sensitive work (public LifeOS releases, security boundaries, irreversible or publish-bound actions). Runs the top Anthropic alias at xhigh effort in a fresh context: a fresh adversarial mind reading the artifact instead of the…
Sol
The OpenAI lane (principal, 2026-10-12, "it's the better model right now"): OpenAI's GPT-6.1 Sol model via codex exec at high reasoning (ID resolved from CROSSVENDOR.sol in models.ts, never pinned in prose), isolated codex home. TWO MODES set by the spawn prompt. BUILD mode (default, workspace-write) is execution for…
architect
USE THIS WHEN symptoms keep recurring, layer boundaries blur, or changes ripple unexpectedly. ALWAYS invoke for structural diagnosis during /unstuck or major refactors. Finds root causes in design, not symptoms. Names tradeoffs explicitly.
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).