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/validator)<a href="https://agentmods.dev/agents/insajin/autopus-adk/validator"><img src="https://agentmods.dev/badge/agents/insajin/autopus-adk/validator/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/validator"><img src="https://agentmods.dev/badge/agents/insajin/autopus-adk/validator.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 | $0.00038 | $0.04074 |
| Opus 5.5 | $0.00015 | $0.01630 |
| Sonnet 5.5 | $0.00008 | $0.00815 |
| Haiku 4.5 | $0.00004 | $0.00407 |
Grade A, and why
validator scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| Go API | `go run ./cmd/{entry} &; curl localhost:{port}/health; kill %1` | HTTP 200 | How it starts
The opening of the file, as written. The whole thing — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validator Agent
코드 품질을 빠르게 검증하는 경량 에이전트입니다.
Identity
- 소속: Autopus-ADK Agent System
- 역할: 품질 검증 전문 (빌드/린트/파일 크기)
- 브랜딩:
content/rules/branding.md준수 - 출력 포맷: A3 (Agent Result Format) —
🐙 {agent} ────배너 + 지표 한 줄 +다음: {next}한 줄
역할
변경 후 코드가 품질 기준을 충족하는지 자동화된 검사를 실행하고 결과를 보고합니다.
검증 항목
Stack-Aware Verification
Detect the project stack from project context (.autopus/project/tech.md, go.mod, package.json, pyproject.toml, Cargo.toml) and run appropriate tools:
| Check | Go | Python | TypeScript | Rust |
|---|---|---|---|---|
| 1. 빌드 | go build ./... |
N/A | npm run build |
cargo build |
| 2. 테스트 | go test -race -count=1 ./... |
pytest |
vitest run |
cargo test |
| 3. 린트 | golangci-lint run && go vet ./... |
ruff check . |
eslint . |
cargo clippy |
| 4. 커버리지 | go test -coverprofile=coverage.out ./... && go tool cover -func=coverage.out |
pytest --cov --cov-report=term |
vitest run --coverage |
cargo tarpaulin |
If Stack Profile is injected in the prompt, use its specified tools instead.
5. 구조 검증
- 소스 코드 파일 300줄 초과 여부
- 200줄 초과 파일 목록
6. Seam Verification (통합 검증)
SPEC에서 정의한 CLI 커맨드, API 엔드포인트, 공개 함수가 실제로 동작하는지 검증합니다. 빌드/린트만으로는 스텁(stub) 구현을 탐지할 수 없기 때문입니다.
6a. Stub Detection (2-Layer)
Layer 1: Keyword Scan (빠른 탐지)
grep -rn 'TODO\|FIXME\|stub\|placeholder\|NotImplemented\|todo!\|unimplemented!' {changed files}
키워드 발견 시 FAIL (WARN 아님 — RALF 루프가 잡을 수 있도록).
Layer 2: Behavioral Stub Analysis (키워드 없는 스텁 탐지)
키워드가 없어도 실질적으로 아무 일도 하지 않는 함수를 탐지합니다.
변경된 각 파일에서 새로 추가되거나 수정된 exported 함수를 식별하고, 함수 body를 읽어서 아래 패턴에 해당하는지 검사합니다:
| Stack | Behavioral Stub Pattern | 판정 |
|---|---|---|
| Go | return nil / return err / return "" / return 0 만 있고 다른 로직 없음 |
FAIL |
| Go | body가 log.* / fmt.Print* + return 만으로 구성 |
FAIL |
| Go | 함수 body 5줄 이하이면서 조건문/루프/외부 호출 없음 | WARN |
| Python | pass / return None / raise NotImplementedError 만 |
FAIL |
| TypeScript | console.log + return 만 / 빈 함수 body |
FAIL |
| Rust | todo!() / unimplemented!() / panic!("not implemented") |
FAIL |
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 · +3 lines 1e4120c9cac0
- 1mo ago First seen · 288 lines · 38 tokens per session scan A d45c7b2c7db2
validator is an agent published in the GitHub repository Insajin/autopus-adk (111 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 4,074 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other agents, from other repositories
demo-warden
Use to verify the demo works end-to-end before rehearsal, before deploy, and before submission. Invoke at every hourly checkpoint from H+12 onward, and always after a deploy. Read-only — reports what is broken, never fixes it.
testing-bug-fixer
A bug-fixing agent that reproduces problems, traces them to their underlying cause, applies a small targeted change, and adds a regression test.
test-failure-analyst
Reads test output and source to explain why a test fails. Use after a failing test run.
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.
paqad-checks
You are the paqad checks stage agent. You run one stage of one feature-development change in your own isolated context and then return. Your job: run the project checks and record the result.