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.
npx skills add Insajin/autopus-adk --skill auto-canarygit 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/skills/insajin/autopus-adk/auto-canary)<a href="https://agentmods.dev/skills/insajin/autopus-adk/auto-canary"><img src="https://agentmods.dev/badge/skills/insajin/autopus-adk/auto-canary/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/skills/insajin/autopus-adk/auto-canary"><img src="https://agentmods.dev/badge/skills/insajin/autopus-adk/auto-canary.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00024 | $0.00681 |
| Opus 5 | $0.00012 | $0.00341 |
| Sonnet 5 | $0.00005 | $0.00136 |
| Haiku 4.5 | $0.00002 | $0.00068 |
Grade A, and why
auto-canary 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 11d 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
auto-canary — 배포 검증 스킬
OMP Invocation
/auto canary .../auto-canary ...- Load detail skill
auto-canaryfor either entrypoint.
Context Profile: canary
- Required: core,canary
- Optional: learning
- Excluded: test,signature
프로젝트: autopus-adk | 모드: full
설명
배포 후 건강 검진을 실행합니다. 빌드, E2E, 브라우저 검사를 순서대로 수행하고 PASS/WARN/FAIL 판정을 냅니다.
Scope Boundary
auto canary는 post-deploy 또는 staging smoke/status gate입니다. 목표는 현재 빌드, endpoint, browser surface가 운영 가능한지 빠르게 판정하고.autopus/canary/latest.json에 최신 상태를 남기는 것입니다.- QAMESH manifest, redacted artifact, run index, repair prompt bundle이 필요하거나 browser/desktop/mobile 사용자 journey를 evidence로 남겨야 하면
auto qa ...를 사용합니다. auto qa release안의canary-explicitlane은 명시된 post-deploy smoke Journey Pack을 release gate에 연결하는 bridge lane입니다. Canary 자체가 전체 QAMESH QA mesh를 대체하지 않습니다.
사용법
/auto canary
/auto canary --url https://example.com
/auto canary --watch 5m
/auto canary --compare abc123
플래그
| Flag | Description |
|---|---|
--url <url> |
브라우저 검진 대상 URL. canary.md의 browser 타깃보다 우선합니다. |
--watch <interval> |
지정 주기로 반복 실행합니다. 기본 5m, 최대 30m. |
--compare <commit> |
저장된 이전 실행 결과와 비교합니다. |
실행 순서
.autopus/project/canary.md에 선언된 build/smoke 검증- canary 설정에 선언된 endpoint/browser health check 실행
- endpoint/browser 건강 검진 수행
- PASS/WARN/FAIL 판정
.autopus/canary/latest.json에 결과 저장
OMP Notes
- 전체 파이프라인 규칙과 검증 체크리스트는
/auto canary라우터 본문을 우선합니다. canary.md가 없으면 설정 부재를 명시하고/auto setup안내를 표시합니다.--compare값은 commit SHA 형식 검증 후 사용합니다.
판정 기준
- PASS: 빌드 OK + 전체 E2E 통과 + 치명적 브라우저 오류 없음
- WARN: 빌드 OK + 일부 E2E 실패 또는 비치명적 브라우저 경고
- FAIL: 빌드 실패 또는 치명적 E2E/브라우저 오류
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.
- 11d ago First seen · 70 lines · 24 tokens per session scan A 62871f3d8ea9
auto-canary is a skill published in the GitHub repository Insajin/autopus-adk (111 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 681 once invoked, about $0.0001 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.
Other skills, from other repositories
ui-testing
Create automated UI tests using Playwright for Streamlit and web applications. Use when writing end-to-end tests, automating UI testing, or testing new features.
playwright
Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions…
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
test-reporting
Run the Level 2 dummy agent integration test suite and produce a detailed HTML report with per-test input → outcome analysis.
android-emulator
Verify and debug native, React Native, Expo, or Flutter apps on an Android Emulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an Android virtual device.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.