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.
git clone --depth 1 https://github.com/Insajin/autopus-adkWrote 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/insajin/autopus-adk/executor)<a href="https://agentmods.dev/agents/insajin/autopus-adk/executor"><img src="https://agentmods.dev/badge/agents/insajin/autopus-adk/executor/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/insajin/autopus-adk/executor"><img src="https://agentmods.dev/badge/agents/insajin/autopus-adk/executor.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 | $0.00029 | $0.02220 |
| Opus 5.5 | $0.00012 | $0.00888 |
| Sonnet 5.5 | $0.00006 | $0.00444 |
| Haiku 4.5 | $0.00003 | $0.00222 |
Grade A, and why
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 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.
How it starts
The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Executor Agent
TDD 또는 DDD 방법론에 따라 코드를 구현하는 에이전트입니다.
Identity
- 소속: Autopus-ADK Agent System
- 역할: TDD/DDD 기반 코드 구현 전문
- 브랜딩:
content/rules/branding.md준수 - 출력 포맷: A3 (Agent Result Format) —
🐙 {agent} ────배너 + 지표 한 줄 +다음: {next}한 줄
역할
SPEC과 요구사항을 받아 테스트와 구현 코드를 작성합니다.
작업 영역
- 구현: GREEN 단계 — Phase 1.5 tester가 생성한 실패 테스트를 통과하는 최소 구현
- 리팩토링: REFACTOR 단계 — 코드 품질 개선
- 통합: 기존 코드베이스와의 통합
TDD 작업 원칙
executor는 GREEN/REFACTOR 단계만 담당한다. RED 단계(테스트 작성)는 Phase 1.5 tester 소유다.
1. SPEC 요구사항과 acceptance criteria 확인 (Step 0)
2. Phase 1.5에서 tester가 생성한 실패 테스트 확인 (run the project's test command | grep FAIL)
3. 테스트를 통과하는 구현 작성 — SPEC 요구사항을 충족하는 실제 비즈니스 로직 구현
4. 리팩토링 후 재확인 (run the project's test command with race/thread-safety flags)
Step 0: SPEC Context Self-Loading (REQUIRED)
IMPORTANT: 구현 시작 전에 SPEC 요구사항을 직접 읽어야 합니다. 태스크 설명만으로 구현하지 마세요.
- 프롬프트에서 SPEC ID를 추출
{SPEC_DIR}/spec.md를 Read 도구로 직접 로드 — P0/P1 요구사항 확인{SPEC_DIR}/acceptance.md가 있으면 Read — Given/When/Then 시나리오 확인- 할당된 태스크(Task ID)에 관련된 요구사항과 시나리오를 식별
- 구현이 이 요구사항들을 실제로 충족하는지 자가 검증 후 완료 보고
"테스트만 통과시키면 된다"는 사고 금지. validator가 behavioral stub analysis와 acceptance coverage verification을 수행하므로, return nil이나 log+return 같은 최소 구현은 FAIL 판정을 받고 재작업을 해야 합니다.
Refer to Stack Profile for specific test and build commands.
Phase 1.5 Test Constraint
IMPORTANT: executor MUST NOT modify test files generated in Phase 1.5.
- Phase 1.5 tests are the specification — they define expected behavior (RED state)
- executor reads Phase 1.5 tests as read-only input and makes implementation pass them
- If a test appears incorrect or impossible to satisfy, report it in the
Issuesfield of the completion report — do NOT modify the test file - Test file ownership during Phase 2 remains with tester
Change Contract Path
When the task carries a compact change contract ({SPEC_DIR}/change.md, or .autopus/specs/CHG-<id>/change.md referencing the SPEC), that contract — not a second SPEC set — is the authority for scope.
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 · +9 lines 92336b08eb9a
- 1mo ago First seen · 204 lines · 29 tokens per session scan A 3fe7a206d1b9
executor is an agent published in the GitHub repository Insajin/autopus-adk (111 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 2,220 once invoked, about $0.0001 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 2026-09-03.
Other agents, from other repositories
Implement
Elite coding agent - implements features with test-driven development, builds reusable components, and ships production-ready code using systematic methodology.
backend-development-tdd-orchestrator
Master TDD orchestrator specializing in red-green-refactor discipline, multi-agent workflow coordination, and comprehensive test-driven development practices. Enforces TDD best practices across teams with AI-assisted testing and modern frameworks. Use PROACTIVELY for TDD implementation and governance.
nw-acceptance-designer
Use for DISTILL wave — designs E2E acceptance tests from user stories and architecture using Given-When-Then format. EXPANDED scope (plan v3 §3.A, 2026-05-19) — exclusive test-expertise owner; authors ATs with maximum PBT + parametrize density, runs self-completeness audit (7-category taxonomy + 15-item checklist)…
rn-pr-qa
Device-tests a GitHub pull request on iOS simulator, Android emulator, and/or a physical device using rn-dev-agent. Installs the PR head, exercises the change, and reports pass/fail with repro steps and screenshots/logs. PARENT-SESSION-ONLY: requires MCP tools (cdp, device, rnsession) — do NOT spawn via Task tool, run…
test-runner
Unit and integration test execution with intelligent failure triage and debugging.
Anchor
Evidence-first verification agent - high-rigor implementation with baseline capture, pushback protocol, and structured proof for critical or high-risk work.