Agent skill
executing-plans
Use when given a complete implementation plan to execute in controlled batches with review checkpoints - loads plan, reviews critically, executes tasks in batches, reports for review between batches
Install this agent skill to your Project
npx add-skill https://github.com/timbuchinger/loadout/tree/main/skills/executing-plans
SKILL.md
Executing Plans
Overview
Load plan, review critically, execute tasks in batches, report for review between batches.
Core principle: Batch execution with checkpoints for review and feedback.
When to Use
- Partner provides a complete implementation plan
- Plan has detailed tasks with verification steps
- Work benefits from checkpoint reviews
- Executing work created by writing-plans skill
The Process
Step 1: Load and Review Plan
- Read the plan file (typically in
docs/plans/) - Review critically - identify any questions or concerns
- Check for:
- Missing information or unclear steps
- Potential blockers or dependencies
- Inconsistencies or gaps in approach
- If concerns: Raise them with your partner before starting
- If no concerns: Create todo list and proceed
Step 2: Execute Batch
Default: First 3 tasks
For each task in the batch:
- Mark task as in_progress in todo list
- Follow each step exactly (plans have bite-sized steps)
- Run all verification steps as specified
- Confirm tests pass and changes work
- Mark task as completed
Follow the plan precisely:
- Execute steps in order
- Run commands as specified
- Verify expected output
- Don't skip verification steps
- Don't deviate from plan unless blocked
Step 3: Report
When batch complete:
- Summarize what was implemented
- Show verification output (test results, command output)
- Highlight any issues or deviations
- Say: "Ready for feedback."
Keep reports concise but complete:
- Which tasks were completed
- Key changes made
- Verification results
- Any concerns or questions
Step 4: Continue
Based on feedback:
- Apply requested changes if needed
- Execute next batch (next 3 tasks)
- Repeat until all tasks complete
Step 5: Complete Development
After all tasks complete and verified:
- Run full test suite
- Verify all changes work together
- Review what was built
- Consider next steps (PR, deployment, etc.)
When to Stop and Ask
STOP executing immediately when:
- Hit a blocker mid-batch (missing dependency, test fails unexpectedly)
- Instructions are unclear or ambiguous
- Verification fails repeatedly
- Discover plan has critical gaps
- Approach seems incorrect
Ask for clarification rather than guessing.
Don't try to work around blockers - stop and get guidance.
When to Revisit Earlier Steps
Return to Review (Step 1) when:
- Partner updates the plan based on feedback
- Fundamental approach needs rethinking
- New information changes requirements
Don't force through blockers - stop and ask.
Best Practices
Be systematic:
- Follow plan order unless advised otherwise
- Complete one task fully before starting next
- Don't skip ahead or batch tasks differently
Be thorough:
- Run all verification steps
- Check for unexpected side effects
- Verify changes work as intended
Be communicative:
- Report clearly at checkpoints
- Flag concerns early
- Ask when uncertain
Be precise:
- Follow instructions exactly
- Use exact file paths from plan
- Run exact commands specified
Example Execution
Batch 1 Report
Completed tasks 1-3:
Task 1: Email Validation
- Created src/validators/email.py
- Created tests/validators/test_email.py
- Tests pass: 2/2 ✓
Task 2: User Model Update
- Modified src/models/user.py
- Added email field validation
- Tests pass: 5/5 ✓
Task 3: API Endpoint
- Created src/api/auth.py
- Integrated email validation
- Tests pass: 3/3 ✓
All verifications passed. Ready for feedback.
Common Mistakes to Avoid
- Don't deviate from the plan without approval
- Don't skip verification steps to save time
- Don't batch more tasks than specified
- Don't continue when blocked
- Don't assume what the plan meant - ask
Quick Reference
| Step | Action | When to Stop |
|---|---|---|
| 1. Load | Review plan critically | Concerns found |
| 2. Execute | Implement 3 tasks | Blocker hit |
| 3. Report | Show results, ask for feedback | - |
| 4. Continue | Next batch based on feedback | All tasks done |
| 5. Complete | Final verification | - |
Final Rule
Follow the plan exactly.
Stop when blocked or uncertain.
Report at checkpoints.
Trust the plan, but verify everything.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
brainstorming
Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes
add-note
Use this skill whenever important information is learned during a task or when the user explicitly asks to store something. Use when users ask to remember. Triggers on "remember this", "update memory", "share" or any persistent storage request.
user-story
Creates well-structured user stories for software development and project management. Use when the user asks to write, create, or format a user story, or needs to document requirements, features, or tasks in user story format.
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first
kubernetes-troubleshoot
Troubleshoot and manage Kubernetes clusters, including resource inspection, debugging, pod logs, events, and cluster operations. Use when the user needs to diagnose issues, inspect workloads, analyze pod failures, or perform Kubernetes cluster operations.
writing-plans
Use when design is complete and you need detailed implementation tasks - creates comprehensive implementation plans with exact file paths, complete code examples, and verification steps assuming minimal codebase familiarity
Didn't find tool you were looking for?