New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Debugger

by antonbabenko in antonbabenko/deliberation

Rank root-cause hypotheses and propose the smallest safe fix.

MITAuto-check passedDevelopment

Install Debugger

skills CLI
$ npx skills add antonbabenko/deliberation --skill debugger -a claude-code

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

GitHub CLI
$ gh skill install antonbabenko/deliberation debugger --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/antonbabenko/deliberation.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/debugger .claude/skills/debugger && 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
debugger
GitHub stars
169
Token cost
~554 tokens
SKILL.md length
310 words
Files
1
Skills in repo
9
Repo updated
First seen
Licence
MIT

At a glance

Rank root-cause hypotheses and propose the smallest safe fix.

  • Works in 4 steps: Restate the reported symptom in one line. → Form hypotheses ranked by likelihood… → For each, give: confidence… → …
  • Tasks that involve Root cause analysis
  • SKILL.md covers Context, Method, Honesty escape (important) and Response Format, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Debugger is an agent skill from antonbabenko/deliberation. Rank root-cause hypotheses and propose the smallest safe fix.

Its SKILL.md is about 550 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Root cause analysis. It works with Model Context Protocol. The repository describes itself as: Ask Codex, Gemini, Grok, and 400+ OpenRouter models (Qwen, Kimi, DeepSeek) for second opinions or arbiter-mediated consensus. One MCP server for Claude Code, Codex, Cursor, Kiro… The licence is MIT.

When your agent uses it

  • Tasks that involve Root cause analysis

Example prompts

  • “/debugger”

Workflow steps

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

  1. Restate the reported symptom in one line.
  2. Form hypotheses ranked by likelihood from the actual evidence.
  3. For each, give: confidence (high/med/low), root cause, the evidence that supports it, how the symptom maps to the cause, a quick way to…
  4. Propose the smallest change that resolves the root cause - not a refactor.

What it can do on your machine

Read from SKILL.md and the folder at commit 7cd0ab5. 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

Debugger loads about 554 tokens when it runs. Until then it costs about 18 tokens; SKILL.md has 310 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~18
When it runs · the whole SKILL.md, loaded when a task matches
~554

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 antonbabenko/deliberation at commit 7cd0ab5, republished under its MIT licence (© antonbabenko). 310 words, ~554 tokens.

Download SKILL.mdSave it as .claude/skills/debugger/SKILL.md (or your agent's skills folder).
name
debugger
description
Rank root-cause hypotheses and propose the smallest safe fix.
<!-- GENERATED by scripts/sync-hosts.js - edit the source under prompts/, AGENTS.md, or examples/, then regenerate. -->

Debugger

You are a debugging specialist. Given a bug report plus whatever code, logs, and context are supplied, you produce ranked root-cause hypotheses and the smallest safe fix - or you state honestly that the evidence shows no bug.

Context

You are an on-demand advisor. Each consultation is standalone. Your access varies by where you run: when you have repo, shell, or test-execution tools, use them to confirm hypotheses; when you do not, reason only from the evidence given. Never fabricate file paths, line numbers, or behavior you have not actually observed.

Method

  1. Restate the reported symptom in one line.
  2. Form hypotheses ranked by likelihood from the actual evidence.
  3. For each, give: confidence (high/med/low), root cause, the evidence that supports it, how the symptom maps to the cause, a quick way to confirm it, the minimal fix, and why that fix will not regress nearby behavior.
  4. Propose the smallest change that resolves the root cause - not a refactor.

Honesty escape (important)

If, after a thorough pass, the evidence shows no concrete bug matching the symptom, do NOT hunt or invent one. Say so, summarize what you examined, and ask 1-3 targeted questions (or name the logs/code) that would let you continue. The report may be a misunderstanding.

Response Format

Bottom line: 1-2 sentences - the most likely cause, or "No bug found in the evidence".

Hypotheses (ranked): each with confidence, root cause, evidence, confirm-step, minimal fix, regression note.

If no bug found: what you examined + the targeted questions to proceed.

<SUMMARY> top hypothesis + confidence + the single next action, under ~120 words </SUMMARY>.

When to Invoke

  • A reported runtime error, crash, test failure, or wrong output.
  • After 2+ failed fix attempts (fresh ranked hypotheses).

When NOT to Invoke

  • A design question (use Architect) or a code-quality pass (use Code Reviewer).
  • When the fix is obvious from a first read.

© antonbabenko, MIT. 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 .agents/skills/debugger of antonbabenko/deliberation.

Open the folder on GitHubat commit 7cd0ab5

Compare with similar skills

Debugger 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.

Debugger compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Debugger this skillantonbabenko/deliberation169—~554Automated safety check: PassMIT
Graph-Based Bug Tracingtirth8205/code-review-graph32k1 repos~287Automated safety check: PassMIT
Octocode Code Researchbgauryy/octocode946—~1.5kAutomated safety check: PassMIT
Binlog Failure Analysismicrosoft/testfx1k3 repos~730Automated safety check: PassMIT
Debugagentic-community/mcp-gateway-registry962—~1.8kAutomated safety check: NotesApache-2.0
Self Healingpskoett/pskoett-ai-skills310—~5.3kAutomated safety check: NotesNone

Similar skills

  • Graph-Based Bug Tracing

    tirth8205/code-review-graph

    Traces a bug through a code knowledge graph, following callers, callees and execution flow before opening source files, within a small token budget.

    32k GitHub starsUsed in 1 repo~287 tokens
    DevelopmentAuto-check passed

  • Octocode Code Research

    bgauryy/octocode

    Researches code with evidence: traces callers, imports and cross-repo links, diagnoses failures and reports findings with exact file and line references and a confidence label.

    946 GitHub stars~1.5k tokensUpdated 4 days ago
    DevelopmentAuto-check passed

  • Binlog Failure Analysis

    microsoft/testfx

    Official

    Analyze MSBuild binary logs to diagnose build failures. An agent skill from microsoft/testfx.

    1k GitHub starsUsed in 3 repos~730 tokens
    DevelopmentAuto-check passed

  • Debug

    agentic-community/mcp-gateway-registry

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

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

  • Self Healing

    pskoett/pskoett-ai-skills

    Active runtime recovery for coding agents: when something breaks mid-task, diagnose the root cause, write a fix, VERIFY by re-running the broken thing, then file a HEAL- entry to .learnings/HEALS.md…

    310 GitHub stars~5.3k tokensUpdated 2 days ago
    DevelopmentAuto-check: notes

  • Acp Live Diagnose

    jrhubott/adaptive-cover-pro

    Root-cause a misbehaving Adaptive Cover Pro cover on a RUNNING Home Assistant install by pulling live diagnostics over the HA MCP, correlating against the recorder, proving the mechanism with a…

    176 GitHub stars~3.8k tokensUpdated 7 days ago
    DevelopmentAuto-check passed

More from antonbabenko/deliberation

All 9 skills in this repo

  • Deliberation

    antonbabenko/deliberation

    When and how to delegate to GPT, Gemini, Grok, and OpenRouter expert subagents via the deliberation MCP tools.

    169 GitHub stars~3.4k tokensUpdated yesterday
    Auto-check passed

  • Architect

    antonbabenko/deliberation

    System design, tradeoffs, and complex technical decisions. An agent skill from antonbabenko/deliberation.

    169 GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed

  • Code Reviewer

    antonbabenko/deliberation

    Find bugs, security holes, and maintainability issues in a diff or file.

    169 GitHub stars~881 tokensUpdated yesterday
    Auto-check passed

  • Plan Reviewer

    antonbabenko/deliberation

    Validate that a work plan is executable before work starts. An agent skill from antonbabenko/deliberation.

    169 GitHub stars~931 tokensUpdated yesterday
    Auto-check passed

  • Researcher

    antonbabenko/deliberation

    Research external libraries, APIs, and best practices, with evidence.

    169 GitHub stars~840 tokensUpdated yesterday
    Auto-check passed

  • Scope Analyst

    antonbabenko/deliberation

    Catch ambiguities and hidden requirements before planning. An agent skill from antonbabenko/deliberation.

    169 GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Debugger

What does Debugger do?

Rank root-cause hypotheses and propose the smallest safe fix. Debugger is an agent skill from antonbabenko/deliberation. Rank root-cause hypotheses and propose the smallest safe fix.

When should I use Debugger?

Debugger fits situations like: tasks that involve Root cause analysis.

How do I install Debugger in Claude Code?

Run `npx skills add antonbabenko/deliberation --skill debugger -a claude-code`. Or copy the skill folder (.agents/skills/debugger in antonbabenko/deliberation) into .claude/skills/debugger in your project. Claude Code loads it when a task matches its description.

How do I install Debugger in Codex?

Run `npx skills add antonbabenko/deliberation --skill debugger -a codex`. Or copy the skill folder (.agents/skills/debugger in antonbabenko/deliberation) into .agents/skills/debugger in your project. Codex loads it when a task matches its description.

Can I use Debugger 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 antonbabenko/deliberation --skill debugger -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/debugger, .gemini/skills/debugger, .github/skills/debugger and .opencode/skills/debugger in your project.

What does Debugger need to run?

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

Does Debugger 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 Debugger 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 Debugger use?

Debugger is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Debugger use?

About 554 tokens (SKILL.md is roughly 2.2k 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 Debugger?

Skills that share tags, products or a category with Debugger: Graph-Based Bug Tracing (tirth8205/code-review-graph, 32k stars), Octocode Code Research (bgauryy/octocode, 946 stars), Binlog Failure Analysis (microsoft/testfx, 1k stars) and Debug (agentic-community/mcp-gateway-registry, 962 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Debugger?

antonbabenko (a GitHub user) maintains it in antonbabenko/deliberation, which has 169 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on October 6, 2026.

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