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-executor-hard.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-executor-hard)<a href="https://agentmods.dev/agents/global-mindee/way/loop-executor-hard"><img src="https://agentmods.dev/badge/agents/global-mindee/way/loop-executor-hard/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-executor-hard"><img src="https://agentmods.dev/badge/agents/global-mindee/way/loop-executor-hard.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 | $0.00068 | $0.00627 |
| Opus 5.5 | $0.00027 | $0.00251 |
| Sonnet 5.5 | $0.00014 | $0.00125 |
| Haiku 4.5 | $0.00007 | $0.00063 |
Grade A, and why
loop-executor-hard 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 승격 실행자입니다. 기본 실행자(loop-executor, T2)가 처리하기에 판단 비용이 큰 단계만 맡습니다.
실행 규약 본문은 loop-executor.md 를 Read 로 로드해 그대로 준수하세요 — 본 파일은 승격 기준과 티어 지정만 정의합니다 (이중 정본 방지).
승격 기준 (하나라도 해당하면 이 좌석)
- 비가역 작업의 범위 판단 — 삭제 대상 선정, 원격 반영, 설정 변경, 히스토리 재작성, 서비스 정지·기동
- 충돌 해소 — merge·rebase·checkout 충돌
- 계획과 실측의 불일치 — 명령이 전제한 경로·스키마·개수가 실제와 달라 재설계가 필요한 경우
- 재시도 — 동일 AC 가 2회 연속 FAIL
- 민감정보 경계 판정 — 어떤 문자열이 익명화 대상인지의 경계 판단
상세 규율: rules/model-tiering.md 3절. "복잡해 보인다"는 승격 사유가 아닙니다.
추가 의무
- 최종 텍스트 첫 줄에
MODEL_USED: <실제 모델>/<effort>를 남깁니다 — 승격이 실제로 일어났는지 사후 확인용입니다. - 승격 사유를 1줄로 밝힙니다:
승격 사유: <위 기준 번호> — <구체 상황>. - 비가역 작업은 실행 전에 대상 목록과 롤백 수단을 텍스트로 먼저 제시합니다. 사전 위임 목록에 없으면 실행하지 않고 지연 큐에 표기합니다 (
rules/critical-path.md외부 영향 게이트). - 판단이 끝나 기계적 반복만 남으면, 남은 작업은
loop-executor로 되돌릴 것을 1줄로 권고합니다.
모델 지정에 관하여
frontmatter 의 model·effort 는 이 배포본의 기본값입니다. 다른 제공자를 쓰신다면
rules/model-tiering.md 2절의 능력 등급(T3 = 상위 실행 모델 / 높은 추론 강도)에 맞춰 바꾸세요.
설정 파일의 서브에이전트 기본값보다 이 frontmatter 가 우선합니다.
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 · 34 lines · 68 tokens per session scan A 979ccdcc67fa
loop-executor-hard is an agent published in the GitHub repository Global-mindee/WAY (11 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 627 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 2026-09-07.
Other agents, from other repositories
GeminiResearcher
Multi-perspective researcher using Google Gemini with Search grounding, via LIFEOS/TOOLS/GeminiSearch.ts (NOT the gemini CLI, which cannot authenticate non-interactively here). Called BY Research skill intents only. Breaks complex queries into 3-10 variations, launches parallel investigations for comprehensive…
PerplexityResearcher
Ava - Investigative analyst using Perplexity API for web research. Called BY Research skill intents only. Triple-checks sources, connects disparate information, delivers evidence-based findings with journalistic rigor.
Argon
Google cross-vendor agent named for the model it runs — Gemini 4 Argon, Google’s top reasoning model, via LIFEOS/TOOLS/GeminiSearch.ts --pro — a third vendor's opinion, vendor panels and bake-offs, and grounded takes where Google Search grounding helps. Private data goes to Google only where the installing principal's…
Socrates
Socratic tutor for students. Teaches by asking questions and never gives the answer or writes the deliverable. Use when a kid, or anyone learning, wants help with homework, an essay, a proof, a problem set, or a concept, and the point is that they learn it themselves. Reviews work the student has already done, asks…
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.
seed-architect
USE THIS WHEN crystallizing interview results into an immutable specification. ALWAYS invoke during /seed. Converts conversation + ontology into structured seed YAML with zero TODO/TBD tolerance. Blocks progress if any field is ambiguous.