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 toss/apps-in-toss-harness --skill debuggit clone --depth 1 https://github.com/toss/apps-in-toss-harnessWrote 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/toss/apps-in-toss-harness/debug)<a href="https://agentmods.dev/skills/toss/apps-in-toss-harness/debug"><img src="https://agentmods.dev/badge/skills/toss/apps-in-toss-harness/debug/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/toss/apps-in-toss-harness/debug"><img src="https://agentmods.dev/badge/skills/toss/apps-in-toss-harness/debug.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 | $0.00126 | $0.09151 |
| Opus 5.5 | $0.00050 | $0.03660 |
| Sonnet 5.5 | $0.00025 | $0.01830 |
| Haiku 4.5 | $0.00013 | $0.00915 |
Grade A, and why
debug scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -o /dev/null -w "%{http_code}" "http://localhost:$PORT/" || true How it starts
The opening of the file, as written. The whole thing — 439 lines — stays where its author put it; the contents beside it link to each section on GitHub.
debug skill
목적
/ait:debug는 미니앱을 두 겹의 환경에서 디버깅하는 경로를 안내한다. 한 명령이
관찰 결과에 따라 환경을 분기한다 (환경 모델·fidelity 사다리: 로컬 docs/design/three-environments-fidelity.md — maintainer-internal 문서, repo 미포함):
| 환경 | 실행 면 | 이 skill의 경로 |
|---|---|---|
| 1. 로컬 브라우저 | desktop Chromium + mock SDK + Panel | 2-A/2-B/3 — panel · window.__ait · 브라우저 DevTools |
| 3. intoss-private relay dev | 실기기 토스 앱 WebView(dogfood) + CDP relay | 5 — start_attach({mode:'relay-staging', scheme_url}) 1호출 QR attach |
환경 번호는 fidelity 사다리의 원 번호를 그대로 쓴다 — 중간 단(환경 2, PWA Sandbox launcher)은 2026-08-10 결정으로 제거됐고 남은 두 단의 번호는 바꾸지 않았다.
디버깅이 아니라 "실제 토스 앱에서 한 번 돌려보고 싶다"면 /ait:test-on-device가
정규 경로다 — 번들 빌드 → 콘솔 업로드 → 컴파일 확인 → 도구가 돌려준 링크로 열기.
이 skill(환경 3)은 그렇게 확인한 뒤 폰에서만 재현되는 문제를 CDP로 관측할 때
쓴다.
- 환경 1은 지금 바로, 의존 없이 쓴다:
@apps-in-toss/devtools의 floating panel — mock 상태(권한·위치·IAP·이벤트 등)를 실시간 관찰·조작 (12개 탭). 증상별로 어느 탭을 볼지는references/panel-tabs.md참조.window.__ait— 런타임 mock SDK 상태 객체. 콘솔이나 에이전트가 직접 읽는다.- 브라우저 기본 DevTools — console / network / sources.
- 환경 3은
ait-devtoolsMCP 서버로 닿는다. 이 서버는 프로젝트 opt-in이다 —/ait:setup-debugger가 프로젝트.mcp.json에 배선하고, 세션에 로드돼 있으면/ait:debug는 새 서버를 띄우지 않고start_attach({mode:'relay-staging', scheme_url})로 환경 전환과 QR attach 경로 발급을 한 호출로 처리한다(아래 5). bootstrap 도구가 세션에 안 보이면 배선이 안 된 것 —/ait:setup-debugger를 먼저 안내한다. QR은 intoss-private deep-link라 토스 앱 WebView가 연다. attach 전에는 bootstrap 도구 (start_debug·start_attach·list_pages·get_debug_status)만 보이고, 폰이 relay에 붙으면 나머지 도구가 같은 세션에서 동적 등록된다.
두 환경 모두 attach 후 run_tests로 미니앱 test case 파일(glob)을 그 환경에서 실행할 수 있다 — 환경 1은 mock + 로컬 CDP, 환경 3은 실 토스 WebView에서 같은 테스트를 돌려 환경별 거동 차이를 본다. 상세는 references/attach-tools.md.
생성·수정하는 모든 메시지에 과장·홍보성 문구를 넣지 않는다. 생성하는 안내는 관찰·진단을 설명하는 최소한으로.
의존
@apps-in-toss/devtools가 devDependencies에 있어야 floating panel을 쓸 수 있다. 없으면/ait:inject-devtools를 먼저 안내한다 (없어도 브라우저 기본 DevTools 가이드는 진행 가능).- 웹 프로젝트면
package.json이 cwd에 있어야 한다. 없으면 프로젝트 루트로 이동 안내. Unity처럼package.json이 없는 스택은 아래 1단계를 따른다. - 환경 1: 에이전트가 필요 시 dev 서버를 자동 기동한다(아래 2-A 사전 기동 블록).
- 환경 3:
ait-devtoolsMCP 서버(@apps-in-toss/debugger)가 세션에 로드돼 있어야 한다 — 프로젝트.mcp.json에 배선돼 있지 않으면/ait:setup-debugger를 먼저 안내한다(opt-in). - 환경 3: candidate 빌드에
@apps-in-toss/debug-console이dependencies로 설치돼 있어야 attach 표면이 남는다(없으면/ait:inject-debug-console먼저 안내 —injectskill의 debug-console facet).
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 439 lines · 126 tokens per session scan A 7d5fa6311b58
debug is a skill published in the GitHub repository toss/apps-in-toss-harness (186 stars, last pushed 3d ago), licensed BSD-3-Clause. It adds 126 tokens to every session and 9,151 once invoked, about $0.0005 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 2026-10-23.
Other skills, from other repositories
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
ci-fixer
CI failures - read error, minimal fix, verify.
diagnosing-missing-recordings
Diagnoses why a session recording is missing or was not captured. Use when a user asks why a session has no replay, why recordings aren't appearing, or wants to troubleshoot session replay capture issues for a specific session ID or across their project. Covers SDK diagnostic signals, project settings, sampling…