How do I install the Code Debug skill?

Run npx skillmds@latest add alexeyshishin/code-debug in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Code Debug safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Code Debug?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Code Debug free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Code Debug?

alexeyshishin (@alexeyshishin) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Code Debug by alexeyshishin — Agent Skill

Name: Code Debug
Author: alexeyshishin

Code Debug

Find the root cause of a bug or failing test. Spawns 1 debugger subagent that reproduces, ladders hypotheses, isolates with evidence, and applies the minimal fix. Use when a test fails, /code-build reports blocked, or "X stopped working". Does NOT design features (that's /code-plan).

alexeyshishin 60313ec 2 files · 3.6 KB Updated Sep 17, 2026

File contents

Skill: /code-debug

ORCHESTRATOR. One debugger subagent. It diagnoses before it touches anything.

Invocation

/code-debug "<error text / failing test / what broke>" (optionally /code-debug <slug> to tie it to a feature build)

Steps

Gather the symptom: the error/stack/failing-test name from the user, plus the build report swarm-report/<slug>-build.md if a slug was given.
Spawn 1 debugger (Task, general-purpose). Prompt:

Answer TERSE. Read .claude/agents/debugger.md and follow it exactly. Symptom: <verbatim error / failing test>. Feature slug (if any): .
Report the debugger's return verbatim: root cause, evidence, fix, and the re-run output.
Route the outcome:
- fixed → suggest /code-review <slug> to check the fix.
- root_cause_found (found but not fixed) or stuck → show the hypothesis ladder; the user decides the fix, or re-run /code-build <slug> with the root cause as input.
- cannot_reproduce → ask the user for exact repro steps; do not guess-patch.

Where it sits in the loop

/code-plan → /code-build → /code-review. If a test fails or review says rework → /code-debug → back to /code-build. The Stop test-gate hook blocks "done" until tests actually run.

Frequently asked questions