what is codex-bug-reproducer fr?

kappaemme-git/codex-bug-reproducer — explained in plain English

Analysis updated 2026-05-18

★ 63PythonAudience · developerComplexity · 2/5LicenseSetup · easy

vibe map

mindmap
  root((bug reproducer))
    What it does
      Scans code for likely bugs
      Ranks candidate bugs
      Proves bugs with tests
    Tech stack
      Codex skill
      Node npx installer
      Python
    Use cases
      Find bugs with no bug report
      Reproduce a known issue
      Verify a fix actually works
    Audience
      Developers
      AI coding agent users
    Safety
      Two approval gates
      Honest evidence labels
      Reproduce only mode

mindmap root((bug reproducer)) What it does Scans code for likely bugs Ranks candidate bugs Proves bugs with tests Tech stack Codex skill Node npx installer Python Use cases Find bugs with no bug report Reproduce a known issue Verify a fix actually works Audience Developers AI coding agent users Safety Two approval gates Honest evidence labels Reproduce only mode

what do people make with this?

VIBE 1

Scan an unfamiliar codebase to find likely bugs without a bug report.

VIBE 2

Turn a stack trace or bug description into a minimal, provable reproduction.

VIBE 3

Verify a proposed bug fix actually resolves the failure with red to green evidence.

VIBE 4

Investigate a codebase for bugs without letting the AI change production code.

what's the stack?

PythonNode.jsCodex

how it stacks up fr

	kappaemme-git/codex-bug-reproducer	frayude/throttnux	huzhe115/datalyze
Stars	63	63	63
Language	Python	Python	Python
Setup difficulty	easy	moderate	moderate
Complexity	2/5	3/5	3/5
Audience	developer	ops devops	data

Figures from each repo's GitHub metadata at analysis time.

how do i run it?

Difficulty · easy time til it works · 5min

Installs with a single npx command into the Codex skills folder, requires restarting Codex.

Use freely for any purpose, including commercial use, as long as you keep the copyright notice.

in plain english

Codex Bug Reproducer is a skill for the Codex AI coding assistant that hunts for real bugs in a codebase and proves whether they are actually bugs before touching any code. You do not need to already know what is broken. It scans contracts, boundaries, state transitions, error paths, and how functions are actually called elsewhere in the code, then ranks the strongest candidate bugs by how much evidence supports them, how reachable they are, and how much impact they would have. A candidate is never just declared a bug from reading the code alone. The tool only counts something as proven once it builds a focused, deterministic test, gets your approval to create it, and watches that test actually fail for the predicted reason. It clearly labels the outcome with an honest status, such as reproduced, not reproduced, inconclusive, or fix proven, rather than guessing. The workflow has two separate approval gates: one before it creates any test or reproduction file, and a second, separate approval before it changes any production code to fix the bug. If its plan changes along the way, it has to stop and ask again rather than assuming earlier permission still applies. It also supports reproduce only mode, which finds and proves bugs without ever touching production code. Every run produces a JSON evidence file and a Markdown report describing the original bug, expected versus actual behavior, the minimal reproduction, the root cause, and any remaining risks. It installs into Codex with a single npx command and is released under the MIT license.

prompts (copy fr)

prompt 1

Use bug-reproducer to scan this codebase for likely bugs and rank the strongest candidates.

prompt 2

Use bug-reproducer to investigate this bug: [describe the bug] and wait for my approval before changing files.

prompt 3

Use bug-reproducer in reproduce-only mode to find and prove bugs without touching production code.

prompt 4

Explain the evidence labels bug-reproducer uses and what FIX_PROVEN actually confirms.

Frequently asked questions