setup-debugger

setup-debugger is a skill for Claude Code from toss/apps-in-toss-harness. It costs 197 tokens per session (3,064 once invoked), scanned A, original, BSD-3-Clause.

A setup tool that adds the project's device-debugging connection to the MCP configuration used by Claude Code or Cursor. MCP is a standard way for an AI coding tool to connect to external tools.

In plain words
What is it for?
It helps configure the debugger so an agent can attach to a mini-app running on a device through the supported CDP relay path.
Why use it?
On-device debugging cannot use the project's device connection until that connection is configured. This makes the project-level opt-in without changing application code.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions Claude Code; mentions Codex.

Part of the ait plugin — 11 skills, 4 commands shipped together

Good fit It helps configure the debugger so an agent can attach to a mini-app running on a device through the supported CDP relay path.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/toss/apps-in-toss-harness/setup-debugger
Install

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.

Any agent
npx skills add toss/apps-in-toss-harness --skill setup-debugger
Clone the repo
git clone --depth 1 https://github.com/toss/apps-in-toss-harness

Made for: Claude Code.

Or install ait, the plugin that ships this one along with the rest of its 11 skills, 4 commands.

Wrote 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.

agentmods badge for setup-debugger

README.md
[![agentmods](https://agentmods.dev/badge/skills/toss/apps-in-toss-harness/setup-debugger/github.svg)](https://agentmods.dev/skills/toss/apps-in-toss-harness/setup-debugger)
Your own site
<a href="https://agentmods.dev/skills/toss/apps-in-toss-harness/setup-debugger"><img src="https://agentmods.dev/badge/skills/toss/apps-in-toss-harness/setup-debugger/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.

agentmods 80×15 button for setup-debugger

Your own site · 80×15
<a href="https://agentmods.dev/skills/toss/apps-in-toss-harness/setup-debugger"><img src="https://agentmods.dev/badge/skills/toss/apps-in-toss-harness/setup-debugger.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 197 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,064 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00197 $0.03064
Opus 5.5 $0.00079 $0.01226
Sonnet 5.5 $0.00039 $0.00613
Haiku 4.5 $0.00020 $0.00306

Measured 6d ago against content hash 92e4cf3a1913, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

setup-debugger 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 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.

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.

packages/agent-plugin/shared/skills/setup-debugger/SKILL.md · 214 lines

How it starts

The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.

setup-debugger skill

목적

/ait:setup-debugger는 on-device 디버깅(/ait:debug §5, 환경 3)이 쓰는 ait-devtools MCP 서버를 현재 프로젝트의 MCP 설정 파일에 등록한다. 이 파일은 호스트마다 다르다 — Claude Code는 .mcp.json, Cursor는 .cursor/mcp.json에 쓴다(판별은 2단계).

이 서버는 plugin manifest에 들어 있지 않다 — 디버깅은 프로젝트 전제 작업이고, 로컬 npx 데몬을 모든 세션에 상시 태우면 idle 비용과 공급망 표면이 생기므로 프로젝트 단위 opt-in이다. 이 skill이 그 opt-in의 단일 경로다.

완료되면:

  • Claude Code면 프로젝트 루트 .mcp.json에, Cursor면 .cursor/mcp.json에 mcpServers."ait-devtools" 항목이 생긴다.
  • Claude Code는 세션에서 서버를 승인·연결하면 /mcp 목록에 ait-devtools가 뜨고, Cursor는 Cursor의 MCP 목록에서 같은 항목을 켜고 승인한다. 연결되면 /ait:debug의 start_attach QR attach 경로(환경 3)가 열린다 — 이 attach 경로는 Claude Code에서 확인된 경로다.

의존

  • cwd가 프로젝트 루트여야 한다 — MCP 설정 파일은 두 호스트 모두 프로젝트 루트 스코프다. 루트가 아니면 이동을 안내하고 중단한다. 이 skill은 앱 코드나 진입점을 건드리지 않으므로 프로젝트가 웹이든 Unity든 엔진 HTML5 빌드든 같은 절차다.
  • npx가 Release tarball(@apps-in-toss/debugger)을 내려받아 실행하므로 전역 설치는 필요 없다. 다만 Node와 npx가 이 머신에 있어야 한다. 앱 스택과는 무관하게 MCP 서버를 띄우는 데만 쓴다.

이 skill은 콘솔 인증을 요구하지 않는다. 로컬 설정 파일 하나만 만진다.

실행 순서

1. 프로젝트 루트 확인

ls package.json

있으면 루트다. 없으면 package.json이 없는 스택일 수 있으니 바로 중단하지 않는다. cwd가 프로젝트 루트인지 확인한다. Unity는 Assets/와 Packages/manifest.json이 있는 디렉터리가 루트다. 엔진 HTML5 빌드 등 그 밖의 스택은 프로젝트 설정 파일이 있는 디렉터리를 찾고, 확신이 없으면 사용자에게 어느 디렉터리에 .mcp.json을 둘지 묻는다. 루트가 아닌 곳이면 중단하고 안내한다:

프로젝트 루트를 찾지 못했습니다. 프로젝트 루트 디렉토리에서 다시 실행해주세요.
예: cd <project-root> && /ait:setup-debugger

2. 호스트 판별 (어느 파일에 쓸지)

1차 근거는 에이전트 자신의 자기 인식이다 — 지금 이 skill을 실행하는 에이전트가 Claude Code인지 Cursor인지는 그 에이전트 자신이 가장 정확히 안다.

보조 신호로 프로젝트 루트의 흔적을 확인한다:

ls -d .cursor .mcp.json .cursor/mcp.json 2>/dev/null
  • Claude Code면 .mcp.json에 쓴다(4단계).
  • Cursor면 .cursor/mcp.json에 쓴다 — .cursor/ 디렉터리가 아직 없으면 먼저 만든다(mkdir -p .cursor).
  • 둘 다 아니면(Codex 등) 이 skill이 지원하는 대상이 아니다 — 아무 파일도 쓰지 않고 그렇게 안내한 뒤 중단한다.
  • 보조 신호가 자기 인식과 어긋나면(흔적이 둘 다 있거나 둘 다 없는데 자신은 분명 Claude Code 또는 Cursor인 경우) 자기 인식을 따른다 — 파일 흔적은 참고일 뿐 판정 근거가 아니다.

3. 기존 MCP 설정 파일 확인 (idempotent)

Read the full file on GitHub · 214 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 6d ago First seen · 214 lines · 197 tokens per session scan A 92e4cf3a1913

Subscribe to this mod's changes

setup-debugger 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 197 tokens to every session and 3,064 once invoked, about $0.0008 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 2026-10-23.

Related

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.

open-metadata/OpenMetadata · 37 tokens

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…

zebbern/claude-code-guide · 71 tokens

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…

adobe/skills · 112 tokens

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.

rmyndharis/antigravity-skills · 36 tokens

ci-fixer

CI failures - read error, minimal fix, verify.

sipyourdrink-ltd/bernstein · 15 tokens

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…

PostHog/posthog · 76 tokens