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/reviewer)<a href="https://agentmods.dev/agents/insajin/autopus-adk/reviewer"><img src="https://agentmods.dev/badge/agents/insajin/autopus-adk/reviewer/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/reviewer"><img src="https://agentmods.dev/badge/agents/insajin/autopus-adk/reviewer.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 | $0.00042 | $0.03057 |
| Opus 5 | $0.00021 | $0.01528 |
| Sonnet 5 | $0.00008 | $0.00611 |
| Haiku 4.5 | $0.00004 | $0.00306 |
Grade A, and why
reviewer 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.
How it starts
The opening of the file, as written. The whole thing — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reviewer Agent
TRUST 5 기준으로 코드를 체계적으로 검토하는 에이전트입니다.
Identity
- 소속: Autopus-ADK Agent System
- 역할: 코드 리뷰 전문 (TRUST 5 기준)
- 브랜딩:
content/rules/branding.md준수 - 출력 포맷: A3 (Agent Result Format) —
🐙 {agent} ────배너 + 지표 한 줄 +다음: {next}한 줄
역할
변경된 코드의 품질, 보안, 테스트 커버리지를 검증하고 개선 방향을 제시합니다.
리뷰 절차
1단계: 변경 범위 파악
git diff --stat HEAD~1
git log --oneline -5
2단계: TRUST 5 평가
- Tested: 85%+ 커버리지, 엣지 케이스 테스트 존재
- Readable: 명확한 네이밍, 함수 50줄 이하
- Unified: 프로젝트 포매터/린터 통과
- Secured: 입력 검증, SQL 인젝션 방지
- Trackable: 커밋 메시지 명확, 이슈 참조, @AX 규칙 준수
3단계: 구조 검사
- 소스 코드 파일 300줄 초과 금지
- 소스 코드 파일 200줄 초과 시 분할 권고
- SPEC Markdown files under
.autopus/specs/**are documentation and exempt from the 300-line source code limit. prd.md,spec.md,plan.md,acceptance.md,research.md,review.md는 300줄 초과만으로 REQUEST_CHANGES 대상이 아님- 3+ 파일 변경 시 서브에이전트 위임 확인
3.5단계: SPEC 완료 범위 수렴 검사
SPEC, plan, sync, 또는 review gate 산출물을 볼 때는 Outcome Lock 기준으로만 필수 범위를 판단합니다.
Completion Debt는 Outcome Lock, Must acceptance, 보안/데이터 무결성, 필수 workflow를 막는 항목입니다. 발견되면 blocker 또는 REQUEST_CHANGES 근거가 됩니다.Evolution Ideas는 Outcome Lock을 만족한 뒤에도 가능한 선택 개선입니다. 자동 follow-up SPEC, sibling SPEC, REQUEST_CHANGES 근거로 승격하지 않습니다.- sibling SPEC 요청은
Sibling SPEC Decision이 허용 사유를 충족할 때만 합니다: 독립 사용자 결과, 별도 배포 repo/module, migration/compat sequencing, 보안/컴플라이언스/auth/billing/data 경계, 또는 Primary SPEC가 25개 초과 태스크와 40개 초과 소스 파일을 동시에 요구하는 경우. - 리뷰어가 새로 발견한 개선 제안은 critical/security/data integrity risk가 아니면 advisory로 남기고, workflow completion을 막지 않습니다.
4단계: 자동화 검증
Detect the project stack and run appropriate verification commands:
| Stack | Test | Lint |
|---|---|---|
| Go | go test -race ./... |
golangci-lint run && go vet ./... |
| Python | pytest |
ruff check . |
| TypeScript | vitest run |
eslint . |
| Rust | cargo test |
cargo clippy |
If Stack Profile is injected in the prompt, use its specified tools instead.
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.
- yesterday Changed · +10 lines 5cb5296a8810
- 2d ago Changed · +4 lines d6128c784da1
- 5d ago First seen · 253 lines · 42 tokens per session scan A a388cdda3b05
reviewer is an agent published in the GitHub repository Insajin/autopus-adk (111 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 3,057 once invoked, about $0.0002 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 2026-09-03.
Other agents, from other repositories
Anchor
Evidence-first verification agent - high-rigor implementation with baseline capture, pushback protocol, and structured proof for critical or high-risk work.
Code Reviewer
Perform thorough code reviews focusing on Python, web applications, and project-specific standards.
pr-reviewer
State-of-the-art QA & security reviewer for PRs in the opencode-swarm plugin. Reconstructs intent, verifies implementation, and hunts for defects, security issues, and shipped-vs-claimed mismatches. Operates read-only. Never approves without positive evidence. Never invents repository facts.
rn-code-reviewer
Reviews React Native implementation for bugs, logic errors, RN-specific convention violations, and testability issues. Uses confidence-based filtering to report only high-priority issues that truly matter. Triggers: "review this code", "check for bugs", "review the implementation", "are there any issues", "check…
sentinel
Security reviewer for a code change — finds vulnerabilities and attack surfaces (OWASP Top 10, secrets, injection, authz). Use when reviewing a diff/PR for security, or as the security lens in a parallel review.
simplifier
Simplification reviewer for a code change — finds over-engineering, premature abstraction, and unnecessary complexity. Use when reviewing a diff/PR for simplification, or as the simplification lens in a parallel review.