Planning strategy for bug fix stories. Activates when fixing defects, correcting unexpected behavior, or resolving errors. Use for root cause analysis with minimal surgical changes.
Plans surgical bug fixes with root cause analysis. Activates when stories mention fixing, resolving, or correcting errors/bugs. Creates minimal-impact implementation plans focused on reproduction steps, root cause, and regression prevention.
/plugin marketplace add elafo/hefesto/plugin install hefesto@hermesThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Plan surgical bug fixes with root cause analysis and regression prevention.
Activate when:
When planning bug fix stories, emphasize:
Before planning, analyze:
Write to {story_path}/plan.md:
# Implementation Plan: {Story Title}
## Metadata
- **Story**: {story_id}
- **Feature**: {feature_id}
- **Type**: bug (inferred)
- **Created**: {timestamp}
- **Severity**: {Low/Medium/High/Critical}
## Bug Description
{Symptoms and user impact}
## Steps to Reproduce
1. {exact step}
2. {exact step}
3. {observe bug}
## Expected vs Actual
| Expected | Actual |
|----------|--------|
| {what should happen} | {what happens} |
## Root Cause Analysis
{Deep analysis of why this is happening - trace the code path}
## Proposed Fix
{Minimal change description - be specific about what will change}
## Code Impact Matrix
| File | Action | Risk | Notes |
|------|--------|------|-------|
| path/to/file | Modify | Low | {minimal change} |
**Scope Constraint**: This matrix should be MINIMAL. If you're touching more than 3-4 files, reconsider the approach.
## Implementation Steps
### Step 1: {Reproduce Bug}
- Confirm bug exists with reproduction steps
- Document current behavior
### Step 2: {Apply Fix}
- **File**: `path/to/file`
- **Change**: {specific change}
- **Why**: {how this addresses root cause}
### Step 3: {Add Regression Test}
- Create test that would have caught this bug
- Ensure test fails before fix, passes after
### Step 4: {Verify Fix}
- Run reproduction steps
- Confirm expected behavior
## Test Strategy
### Regression Test (Required)
- [ ] Test that reproduces the bug (must fail before fix)
### Related Tests
- [ ] {existing tests to run}
## Verification Commands
```bash
# Before fix: reproduce bug
{command to show bug}
# After fix: verify resolution
{command to show fix works}
# Run test suite
{test command}
{How to undo - usually just revert the commit}
{Any context for future developers}
## Constraints
**CRITICAL - Bug fixes have strict boundaries:**
- NO new features
- NO refactoring
- NO "while we're here" changes
- NO scope creep
- ONLY fix the reported bug
If you find other issues during investigation, create separate stories for them.
## Applying This Skill
When creating a bug plan:
1. Document exact reproduction steps first
2. Investigate and understand root cause deeply
3. Propose the smallest possible fix
4. Plan regression test that would catch this bug
5. Define clear before/after verification
6. Keep the scope extremely tight
7. Create separate stories for any other issues found
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.