Bug triage and fix plan: Multi-Step Agent Workflow for Claude Code, Codex or ChatGPT
Reproduces a reported bug, finds the cause in the repo, proposes a fix plan and waits for approval before editing code.
The prompt
Installs to .agents/skills/bug-triage-and-fix-plan-multi-step-agent-workflow-for-claude-cod/
mkdir -p .agents/skills/bug-triage-and-fix-plan-multi-step-agent-workflow-for-claude-cod && curl -sL "https://prompts-gpt.com/prompts/bug-triage-and-fix-plan-multi-step-agent-workflow-for-claude-code-codex-or-chatgpt/raw" -o .agents/skills/bug-triage-and-fix-plan-multi-step-agent-workflow-for-claude-cod/SKILL.md---
name: bug-triage-and-fix-plan
description: Reproduces a reported bug, finds the cause in the repo, proposes a fix plan and waits for approval before editing code. Use when asked to run the "Bug triage and fix plan" workflow.
---
# Bug triage and fix plan
Reproduces a reported bug, finds the cause in the repo, proposes a fix plan and waits for approval before editing code.
## Inputs
Ask for any of these that the user hasn't given:
- `issue` (e.g. "Saving a prompt with an emoji in the title returns 500")
- `code_context` (e.g. "Paste the stack trace and the function(s) involved (e.g. slugify in src/lib/prompts/utils.ts)")
## Steps
Run the steps in order. Refer to saved results by name. Don't skip a step that says STOP.
1. **Issue labelled bug** — Start: Runs when an issue gets the bug label, or by hand with `issue`.
2. **Reproduce** — Using `code_context`, write the smallest failing test or command that shows `issue`. Don't change app code yet. If the context isn't enough, list exactly what's missing. Save the result as `repro`.
3. **Find the cause** — Trace `repro` to the line that fails. Explain why in two sentences. Save the result as `cause`.
4. **Approve the fix plan** — STOP and ask the user to approve before continuing: Show the plan: files to change, the test, the risk. Wait for go-ahead.
5. **Fix and verify** — Apply the plan, run the test suite, and report what changed. Save the result as `result`.
6. **Open a PR** — Finish: Open a PR that links the issue and includes `repro` and `cause`.
## Done when
Every step has run, each approval was given, and you've reported what was produced and where it was saved.Run it in Claude Code or Codex: save as .claude/skills/bug-triage-and-fix-plan/SKILL.md (or .agents/skills/ for Codex) and say "run the Bug triage and fix plan workflow"; parallel steps run as subagents. Or paste it into ChatGPT or Claude and answer its questions. It asks for: issue, code_context. Build or run it step by step at prompts-gpt.com/workflows/bug-triage-and-fix-plan.
Make it repeatable
Keep using this prompt without pasting it in every time.
Prompt details
- By
- Prompts-GPT editors
- Published
Did this prompt work?
Keep exploring
More like this
AGENTS.md Writer: Agent Skill (SKILL.md) for Claude Code, Codex and Cursor
Writes or refreshes a repo's AGENTS.md or CLAUDE.md from what's actually in the code: verified build, test and lint commands, a directory map, conventions, do and don't lists, and gotchas, kept under about 150 lines.
Code Review Checklist: Agent Skill (SKILL.md) for Claude Code, Codex and Cursor
Reviews a diff for correctness, security, performance and tests, and reports findings as file:line with a fix.
Domain Model And ADRs: Agent Skill (SKILL.md) for Claude Code, Codex and Cursor
Builds a glossary of the domain's terms from code and conversation, picks one canonical name for each concept, stress-tests the model against edge cases, writes architecture decision records (ADRs) for non-obvious choices, and flags code names that disagree.
Frontend Taste: Agent Skill (SKILL.md) for Claude Code, Codex and Cursor
Builds pages and components that don't look AI-generated: picks a design direction first, uses real copy, sets hierarchy, covers empty, loading and error states, and avoids common tells like purple gradients and emoji icons.
Systematic Debugging: Agent Skill (SKILL.md) for Claude Code, Codex and Cursor
Hunts down bugs whose cause isn't obvious: flaky or intermittent failures, 'works locally but fails in CI', regressions nobody can place, or a fix that didn't stick.
TDD In Vertical Slices: Agent Skill (SKILL.md) for Claude Code, Codex and Cursor
Implements a feature test-first, one small user-visible behavior at a time: write a failing test, confirm it fails for the right reason, write the least code to pass, refactor while green, checkpoint, and log each cycle.
- Verify Before Done: Agent Skill (SKILL.md) for Claude Code, Codex and Cursor
- Write An Implementation Plan: Agent Skill (SKILL.md) for Claude Code, Codex and Cursor
- Feature idea to spec and tickets: Multi-Step Agent Workflow for Claude Code, Codex or ChatGPT
- Agent Session Handoff Brief with Resume Checklist and Verified State
- Customer feedback to themes and roadmap asks: Multi-Step Agent Workflow for Claude Code, Codex or ChatGPT
- Document intake: classify, extract and verify: Multi-Step Agent Workflow for Claude Code, Codex or ChatGPT