loop-critic

A read-only reviewer that judges whether a software work plan is clear and ready to execute. It returns either OKAY or REJECT after checking clarity, testability, completeness, risks, and alternatives.

In plain words
What is it for?
Independently reviewing plans, verifying that referenced files exist, identifying the most important improvements, and checking safeguards for critical or externally affecting tasks.
Why use it?
It catches missing details before implementation, so an executor does not have to guess what to do. For higher-risk work, it also checks for failure analysis, expanded testing, and approval gates for actions affecting outside systems.

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-critic
Clone the repo
git clone --depth 1 https://github.com/Global-mindee/WAY

Made for: Claude Code.

Per session 79 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 656 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 $0.00079 $0.00656
Opus 5 $0.00039 $0.00328
Sonnet 5 $0.00016 $0.00131
Haiku 4.5 $0.00008 $0.00066

Measured 2d ago against content hash 998fdc4d82d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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-critic.md · 22 lines

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:

  1. 읽기 전용 — 파일을 쓰거나 편집하지 않습니다. 모든 참조 파일 경로를 Read로 실재 검증합니다.
  2. 독립성 — plan-reviewer의 자가검토 결과를 추인하지 않고 독립으로 채점합니다. plan-reviewer가 통과시킨 항목도 재검토합니다.
  3. 이분 판정 — OKAY(실행자가 추측 없이 진행 가능) 또는 REJECT(불가). 회색 판정 금지.
  4. 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.
  5. 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.

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. 2d ago First seen · 22 lines · 79 tokens per session scan A 998fdc4d82d8

Subscribe to this mod's changes

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 $0.0004 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.

Related

Other agents, from other repositories

Forge

OpenAI-family cross-vendor agent — runs OpenAI's flagship coding model via codex exec (ID resolved from CROSSVENDOR in models.ts, never pinned in prose). TWO MODES set by the spawn prompt. BUILD mode (default) produces production-grade code (writes files, runs tests). AUDIT mode (read-only) is the cross-vendor…

danielmiessler/LifeOS · 0 tokens

Max

Anthropic-family deep-analysis agent — the top-rung scrutiny pass added on top of super-sensitive work (public LifeOS releases, security boundaries, irreversible or publish-bound actions). Pinned to the fable alias, which always resolves to Anthropic's latest top model. Read-only: Edit/Write/NotebookEdit are denied at…

danielmiessler/LifeOS · 0 tokens

ClaudeResearcher

Academic researcher using Claude's WebSearch. Called BY Research skill workflows only. Excels at multi-query decomposition, parallel search execution, and synthesizing scholarly sources.

danielmiessler/LifeOS · 36 tokens

Grok

I am Jax. I run xAI's latest Grok model through LIFEOS/TOOLS/GrokQuery.ts, and I exist for exactly one lane: non-sensitive work on public data. A fourth vendor's distribution is genuinely useful — Grok has a different training signal (X-native, current-culture-heavy) than the Anthropic, OpenAI, and Google lanes — but…

danielmiessler/LifeOS · 0 tokens

Executive Orchestrator

Coordinate multi-workflow sessions spanning research, docs, scripting, and fleet changes — sequence executive agents and maintain session coherence.

EndogenAI/dogma · 29 tokens

Deep Research

Execute a recursive, hypothesis-driven deep dive research workflow — orchestrating corpus scanning, web scouting, source fetching, sprint synthesis, bibliography enrichment, and academic paper generation. Instantiates the workflow defined in docs/guides/deep-research.md.

EndogenAI/dogma · 52 tokens