smithery.ai

codex-debug

Use for systematic debugging and root cause analysis with Codex. Triggers on "codex debug", "codex root cause", "have codex investigate this bug", "codex find the issue".

First seen Apr 22, 2026

Installation

$ npx skills add https://smithery.ai

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from smithery.ai · top by installs.

npx skills add https://smithery.ai

Browse all from smithery.ai

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 1,447 B
  • docs SUMMARY.md 189 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 4 installs

SKILL.md

Codex Debug Skill

Systematic debugging and root cause analysis with Codex (gpt-5.2).

When to Use

  • Debugging complex bugs
  • Finding root causes of issues
  • Investigating mysterious errors
  • Performance issue diagnosis
  • Race conditions or timing issues

Reasoning Level

xhigh (debugging requires deep analysis)

Execution

  1. Gather all relevant information:

- Error messages - Stack traces - Relevant code files - Reproduction steps

  1. Formulate a debugging prompt:

``` Debug this issue systematically.

Issue: <description>

Error/Symptoms: <error messages, behavior>

Relevant Code: <file contents>

Please: 1. Identify possible causes 2. Analyze each potential root cause 3. Determine the most likely cause 4. Suggest a fix ```

  1. Run: codex exec -c modelreasoningeffort="xhigh" "<prompt>"
  2. Return the debugging analysis with fix recommendation

Response Format

**Codex Debug Analysis:**

**Issue Summary:**
[What's happening]

**Root Cause Investigation:**
[Step-by-step analysis of potential causes]

**Most Likely Cause:**
[Primary hypothesis with evidence]

**Recommended Fix:**
[Specific fix with code if applicable]

**Session ID:** [id]