debug-driven — tool profile and history

Hypothesis-driven debug mode for Claude Code, Codex, and other agent platforms. Instead of guessing fixes, the agent generates root cause hypotheses, instruments your code with targeted runtime logs, asks you to reproduce via structured choices, analyzes the evidence, applies a targeted fix, then cleans up all instrumentation automatically.

Dormant

Canonical source ↗

Language
JavaScript
License
MIT
Created
Last activity
Topics
  • ai
  • claude-code
  • claude-code-skills
  • claude-skills
  • claudeai
  • codex
  • codex-cli
  • debug-mode
  • debugging
  • skill

Install git clone https://github.com/rgnicoara/debug-driven ~/.claude/skills/debug-driven

Current measurement

2GitHub stars+1 (+100.0 %)
measured growth

Momentum uses available readings from the last 7 days: measured with at least two comparable readings, estimated otherwise.

Reading history

90 days · 90 maximum readings
DateValueMetric
2GitHub stars
2GitHub stars
2GitHub stars
1GitHub stars
1GitHub stars
1GitHub stars
1GitHub stars
1GitHub stars
1GitHub stars
1GitHub stars
1GitHub stars
1GitHub stars
1GitHub stars
1GitHub stars
1GitHub stars
1GitHub stars
1GitHub stars
1GitHub stars
1GitHub stars
1GitHub stars
1GitHub stars
1GitHub stars
1GitHub stars
1GitHub stars

Classifications

Domains
Type
Agent skills
Use cases