Planning strategy for maintenance and chore stories. Activates when refactoring code, updating dependencies, or performing technical maintenance. Use for behavioral-change-free improvements.
Plans maintenance work with zero behavioral changes for refactoring and upgrades.
/plugin marketplace add eLafo/hefesto/plugin install elafo-hefesto-2@eLafo/hefestoThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Plan maintenance work with zero behavioral changes.
Activate when:
When planning chore stories, emphasize:
Before planning, establish:
Write to {story_path}/plan.md:
# Implementation Plan: {Story Title}
## Metadata
- **Story**: {story_id}
- **Feature**: {feature_id}
- **Type**: chore (inferred)
- **Created**: {timestamp}
- **Risk Level**: {Low/Medium/High}
## Chore Description
{Technical work to be done and why}
## Scope
### In Scope
- {specific item to change}
- {specific item to change}
### Out of Scope
- {what NOT to touch}
- {tempting but unrelated changes}
## Before/After Metrics (if applicable)
| Metric | Before | Target After |
|--------|--------|--------------|
| Test coverage | X% | >= X% |
| Build time | Xs | <= Xs |
| Bundle size | X KB | <= X KB |
| {other metric} | {value} | {target} |
## Code Impact Matrix
| File | Action | Risk | Notes |
|------|--------|------|-------|
| path/to/file | Modify/Delete/Move | Low/Med | {description} |
## Implementation Steps
### Step 1: {Establish Baseline}
- Run all tests, confirm passing
- Record baseline metrics
- Create safety checkpoint
### Step 2: {First Change}
- **File**: `path/to/file`
- **Action**: {what to do}
- **Verify**: Run tests after change
### Step 3: {Next Change}
...
### Step N: {Final Verification}
- Run full test suite
- Compare metrics to baseline
- Confirm no behavioral changes
## Test Strategy
### Pre-Chore Verification
- [ ] All existing tests pass
### Post-Chore Verification
- [ ] All existing tests still pass
- [ ] No new test failures
- [ ] Metrics meet targets
## Validation Commands
```bash
# Baseline (run before changes)
{test command}
{metrics command}
# After each step
{test command}
# Final validation
{full test suite}
{metrics comparison}
{How to undo - git revert or specific steps}
{Technical context, future considerations}
## Constraints
**CRITICAL - Chores have strict behavioral boundaries:**
- NO behavioral changes
- NO new features
- Tests must pass BEFORE and AFTER
- All existing functionality must work identically
- Document any performance changes
If you discover bugs during the chore, create separate bug stories.
## Applying This Skill
When creating a chore plan:
1. Define exact scope boundaries upfront
2. Establish baseline metrics before any changes
3. Plan incremental changes with test runs between each
4. Never combine refactoring with behavioral changes
5. Ensure test coverage exists before refactoring
6. Create separate stories for bugs found
7. Verify metrics meet targets at the end
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 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 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.