Agent skill

Agent Debug

by DmNote-App in DmNote-App/DmNote

원인이 불명확한 버그를 독립 서브에이전트와 병렬로 추적한다. An agent skill from DmNote-App/DmNote.

GPL-3.0Auto-check passed

Install Agent Debug

skills CLI
$ npx skills add DmNote-App/DmNote --skill agent-debug -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install DmNote-App/DmNote agent-debug --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/DmNote-App/DmNote.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/agent-debug .claude/skills/agent-debug && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
agent-debug
GitHub stars
2.6k
Token cost
~249 tokens
SKILL.md length
97 words
Files
1
Skills in repo
7
Repo updated
First seen
Licence
GPL-3.0

At a glance

원인이 불명확한 버그를 독립 서브에이전트와 병렬로 추적한다. An agent skill from DmNote-App/DmNote.

  • Works in 5 steps: 메인이 증상·기대 동작·재현 조건을 정리하고 codebase-memory… → Agent(general-purpose, model 생략해 메인 상속,… → 양쪽 분석을 종합해 원인을 확정한다. 추가 확인이 필요하면… → …
  • SKILL.md covers 조사 프롬프트 and 출력
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Agent Debug is an agent skill from DmNote-App/DmNote. 원인이 불명확한 버그를 독립 서브에이전트와 병렬로 추적한다. 여러 서브시스템에 걸치거나 재현이 어려운 버그에 사용자가 직접 호출.

Its SKILL.md is about 250 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Make it yours. A customizable key viewer for DJMAX RESPECT V and any game. The licence is GPL-3.0.

Example prompts

  • “/agent-debug”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. 메인이 증상·기대 동작·재현 조건을 정리하고 codebase-memory 그래프 도구(search_graph, trace_call_path, detect_changes)로 의심 범위와 가설을 세운다. 원인이 한 파일 안에서 명확하면 서브에이전트…
  2. Agent(general-purpose, model 생략해 메인 상속, 백그라운드)에게 사실 정보만 넘겨 독립 조사를 맡긴다. 메인의 가설은 넘기지 않는다.
  3. 양쪽 분석을 종합해 원인을 확정한다. 추가 확인이 필요하면 SendMessage로 같은 에이전트에 가장 효율적인 확인 1개를 요청한다.
  4. 수정은 메인이 최소 범위로 직접 한다. 재현 절차나 테스트로 검증하고, 기능 변경 수준이면 /agent-review.
  5. 서브에이전트가 실패하거나 조사가 2회 불충분하면 그 사실을 명시하고 메인 단독으로 전환한다.

What it can do on your machine

Read from SKILL.md and the folder at commit baac1e8. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Agent Debug loads about 249 tokens when it runs. Until then it costs about 21 tokens; SKILL.md has 97 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~21
When it runs · the whole SKILL.md, loaded when a task matches
~249

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from DmNote-App/DmNote at commit baac1e8, republished under its GPL-3.0 licence (© DmNote-App). 97 words, ~249 tokens.

Download SKILL.mdSave it as .claude/skills/agent-debug/SKILL.md (or your agent's skills folder).
name
agent-debug
description
원인이 불명확한 버그를 독립 서브에이전트와 병렬로 추적한다. 여러 서브시스템에 걸치거나 재현이 어려운 버그에 사용자가 직접 호출.
disable-model-invocation
true
argument-hint
[증상/에러 메시지/재현 방법]

디버깅 독립 조사

  1. 메인이 증상·기대 동작·재현 조건을 정리하고 codebase-memory 그래프 도구(search_graph, trace_call_path, detect_changes)로 의심 범위와 가설을 세운다. 원인이 한 파일 안에서 명확하면 서브에이전트 없이 바로 고친다.
  2. Agent(general-purpose, model 생략해 메인 상속, 백그라운드)에게 사실 정보만 넘겨 독립 조사를 맡긴다. 메인의 가설은 넘기지 않는다.
  3. 양쪽 분석을 종합해 원인을 확정한다. 추가 확인이 필요하면 SendMessage로 같은 에이전트에 가장 효율적인 확인 1개를 요청한다.
  4. 수정은 메인이 최소 범위로 직접 한다. 재현 절차나 테스트로 검증하고, 기능 변경 수준이면 /agent-review.
  5. 서브에이전트가 실패하거나 조사가 2회 불충분하면 그 사실을 명시하고 메인 단독으로 전환한다.

조사 프롬프트

당신은 DmNote(Tauri + React)의 독립 디버거입니다. READ-ONLY: 코드를 수정하지 말고 원인 분석만 보고하세요. 빌드·테스트 실행은 가능합니다.
작업 디렉토리: (절대 경로)
증상: $ARGUMENTS / 기대 동작: ... / 재현 조건: ... / 관련 파일·함수: ... / 최근 변경: ...
요청: 원인 후보와 근거, 재현 가능하면 최소 절차와 직접 검증 결과, 미확정 시 가장 효율적인 추가 확인 1개.
출력: ## 원인 후보 / ## 재현 결과 / ## 추가 확인 필요

출력

문제 요약 → 원인 → 수정·검증 → 남은 리스크

© DmNote-App, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/agent-debug of DmNote-App/DmNote.

Open the folder on GitHubat commit baac1e8

Compare with similar skills

Agent Debug next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Agent Debug compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Agent Debug this skillDmNote-App/DmNote2.6k—~249Automated safety check: PassGPL-3.0
Debugasgeirtj/system_prompts_leaks69k—~439Automated safety check: PassCC0-1.0
Debugparcadei/Continuous-Claude-v33.9k1 repos~1.3kAutomated safety check: PassMIT
Debugcodewhale-hq/Codewhale41k—~195Automated safety check: PassMIT
NanoClaw Container Debuggingnanocoai/nanoclaw31k—~3.8kAutomated safety check: NotesMIT
DebugLuisaGroup/LuisaCompute1.1k—~2.3kAutomated safety check: PassApache-2.0

Similar skills

  • Debug

    asgeirtj/system_prompts_leaks

    Enable debug logging for this session and help diagnose issues

    69k GitHub stars~439 tokensUpdated today
    Auto-check passed
  • Debug

    parcadei/Continuous-Claude-v3

    Debug issues by investigating logs, database state, and git history

    3.9k GitHub starsUsed in 1 repo~1.3k tokens
    DevelopmentAuto-check passed
  • Debug

    codewhale-hq/Codewhale

    Reproduce, minimize, localize, identify root cause, and distinguish diagnosis from an authorized fix.

    41k GitHub stars~195 tokensUpdated today
    DevelopmentAuto-check passed
  • Troubleshooting guide for NanoClaw's containerized agents: where the logs are, how the two session databases show message flow, and how to raise the log level.

    31k GitHub stars~3.8k tokensUpdated yesterday
    DevelopmentAuto-check: notes
  • Debug

    LuisaGroup/LuisaCompute

    Debug crashes and test failures via stack-traces, host/device logging, and DSL buffer inspection.

    1.1k GitHub stars~2.3k tokensUpdated today
    DevelopmentAuto-check passed
  • Debug

    agentic-community/mcp-gateway-registry

    Debug issues in the MCP Gateway Registry using first-principles thinking.

    964 GitHub stars~1.8k tokensUpdated yesterday
    DevelopmentAuto-check: notes

More from DmNote-App/DmNote

  • Codebase Memory Exploring

    DmNote-App/DmNote

    This skill should be used when the user asks to "explore the codebase", "understand the architecture", "what functions exist", "show me the structure", "how is the code organized", "find functions…

    2.6k GitHub stars~576 tokensUpdated today
    Auto-check passed
  • Codebase Memory Quality

    DmNote-App/DmNote

    This skill should be used when the user asks about "dead code", "find dead code", "detect dead code", "show dead code", "dead code analysis", "unused functions", "find unused functions"…

    2.6k GitHub stars~683 tokensUpdated today
    Auto-check passed
  • Codebase Memory Reference

    DmNote-App/DmNote

    This skill should be used when the user asks about "codebase-memory-mcp tools", "graph query syntax", "Cypher query examples", "edge types", "how to use searchgraph", "querygraph examples", or needs…

    2.6k GitHub stars~1.7k tokensUpdated today
    Auto-check passed
  • Codebase Memory Tracing

    DmNote-App/DmNote

    This skill should be used when the user asks "who calls this function", "what does X call", "trace the call chain", "find callers of", "show dependencies", "what depends on", "trace call path"…

    2.6k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Agent Plan

    DmNote-App/DmNote

    구현 전 독립 서브에이전트에게 계획을 검증받는다. An agent skill from DmNote-App/DmNote.

    2.6k GitHub stars~234 tokensUpdated today
    Auto-check passed
  • Agent Review

    DmNote-App/DmNote

    독립 서브에이전트의 적대적 코드 리뷰. An agent skill from DmNote-App/DmNote.

    2.6k GitHub stars~307 tokensUpdated today
    Auto-check passed

Questions about Agent Debug

What does Agent Debug do?

원인이 불명확한 버그를 독립 서브에이전트와 병렬로 추적한다. An agent skill from DmNote-App/DmNote. Agent Debug is an agent skill from DmNote-App/DmNote. 원인이 불명확한 버그를 독립 서브에이전트와 병렬로 추적한다.

How do I install Agent Debug in Claude Code?

Run `npx skills add DmNote-App/DmNote --skill agent-debug -a claude-code`. Or copy the skill folder (.claude/skills/agent-debug in DmNote-App/DmNote) into .claude/skills/agent-debug in your project. Claude Code loads it when a task matches its description.

How do I install Agent Debug in Codex?

Run `npx skills add DmNote-App/DmNote --skill agent-debug -a codex`. Or copy the skill folder (.claude/skills/agent-debug in DmNote-App/DmNote) into .agents/skills/agent-debug in your project. Codex loads it when a task matches its description.

Can I use Agent Debug in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add DmNote-App/DmNote --skill agent-debug -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-debug, .gemini/skills/agent-debug, .github/skills/agent-debug and .opencode/skills/agent-debug in your project.

What does Agent Debug need to run?

SKILL.md names no scripts, command-line tools or credentials: Agent Debug is instructions for the agent only.

Does Agent Debug access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Agent Debug safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Agent Debug use?

Agent Debug is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Agent Debug use?

About 249 tokens (SKILL.md is roughly 996 characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Agent Debug?

Skills that share tags, products or a category with Agent Debug: Debug (asgeirtj/system_prompts_leaks, 69k stars), Debug (parcadei/Continuous-Claude-v3, 3.9k stars), Debug (codewhale-hq/Codewhale, 41k stars) and NanoClaw Container Debugging (nanocoai/nanoclaw, 31k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agent Debug?

DmNote-App (a GitHub organization) maintains it in DmNote-App/DmNote, which has 2,644 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 7, 2026.

Source: DmNote-App/DmNote on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.