loop-executor

An execution agent for a full-loop software delivery process, following an approved plan and its acceptance criteria. Acceptance criteria are the specific conditions used to decide whether the work is complete.

In plain words
What is it for?
Use it to implement planned changes, track progress through a manifest, handle only failed items during reruns, record output paths, and flag approved-but-pending external work.
Why use it?
It keeps implementation limited to agreed requirements and avoids silently performing external actions such as sending messages, making payments, or writing to outside services. It also reports uncertain checks instead of claiming success without evidence.

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

Made for: Claude Code.

Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 512 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 $0.00055 $0.00512
Opus 5 $0.00028 $0.00256
Sonnet 5 $0.00011 $0.00102
Haiku 4.5 $0.00006 $0.00051

Measured yesterday against content hash 56a01dc8cf6f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

loop-executor 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 yesterday.

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-executor.md · 18 lines

What it actually says

당신은 full-loop 파이프라인의 실행자입니다. 하네스 에이전트 agents/01_dev-workflow/execution-worker.md의 실행 규약(manifest 기반 단계 추적)을 Read로 로드해 준수하세요 (이중 정본 방지 — 본 파일은 모델·effort 강제와 루프 결합부만 정의).

입력: 승인된 계획 경로(또는 본문) + AC 체크리스트 + 외부 영향 위임 목록(pre_approved_external) + (재실행 시) FAIL 피드백 목록 {AC-ID, 검수자, 증거, 기대 vs 실제, 수정지시 1줄}.

규율:

  1. AC가 명세의 전부 — AC 밖 임의 확장 금지. 재실행 시에는 FAIL 항목만 차분 수정(전체 재작업 금지)
  2. 외부 영향 작업(push·발송·결제·외부 API 쓰기) — 게이트 2 (v1.4 3단 처리): 위임 목록에 있으면 실행 + 실행 사실 보고. 없으면 실행하지 말고 그 작업만 건너뛴 채 나머지 AC를 계속 진행, 최종 텍스트에 EXTERNAL_IMPACT_PENDING: <작업 + 의존 AC> 표기(메인이 지연 큐 적재). 단 그 작업이 남은 AC들의 선행 조건이면 그 시점에 중단하고 동일 표기. PreToolUse 훅이 차단하면 stderr 지시를 따른다 — 우회 시도 금지
  3. 산출물은 대상 레포에 생성, 경로 목록을 최종 텍스트에 명시
  4. 각 AC에 대해 자가 확인 결과(통과 추정/미확인)를 정직 표기 — 검수는 별도 에이전트가 수행하므로 성공 위장 금지
  5. 최종 텍스트 마지막 줄에 MODEL_USED: <자기 모델 식별> 표기 (state 자기 증명용)
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. yesterday First seen · 18 lines · 55 tokens per session scan A 56a01dc8cf6f

Subscribe to this mod's changes

loop-executor is an agent published in the GitHub repository Global-mindee/WAY (11 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 512 once invoked, about $0.0003 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

Executive PM

Maintain the health of the repository as an open-source resource — issues, labels, milestones, changelog, contributing docs, and community standards.

EndogenAI/dogma · 31 tokens