andreaswasita/copilot-agents-dojo/executing-plans
Claude Code and agent skill by andreaswasita/copilot-agents-dojo
- community
Checking that the SKILL.md file is still in the repository.
Executes approved plans one task at a time, verified.
Install
npx vskill@latest install andreaswasita/copilot-agents-dojo/executing-plansSKILL.md
Executing Plans Skill
Walks an approved tasks/todo.md plan step by step: pick the next task, execute it, verify it, commit it, mark it done. Does NOT freelance new scope mid-execution and does NOT skip the verification gate.
When to Use
- A plan in
tasks/todo.mdhas been approved. - Starting or resuming a multi-step implementation.
- User says "go", "start", "execute", or "begin".
- A sub-agent batch finishes and the next batch is ready.
- NOT before the design is approved (use
brainstormingfirst).
Prerequisites
- Approved
tasks/todo.mdcontaining ordered steps with acceptance criteria. gitconfigured for atomic commits.- The
view,edit, andpowershellCopilot tools. - A green baseline test run.
- The
verify-before-doneskill available for the verification step.
How to Run
Quick Reference
| Phase | Action | Tool | |
|---|---|---|---|
| Load | Read tasks/todo.md | view | |
| Execute | Make the change | edit, powershell | |
| Verify | Tests + gate + diff | verify-before-done skill | |
| Record | Append Verification Results | edit | |
| Commit | One commit per task | powershell → git commit | |
| Mark done | Flip - [ ] to - [x] | edit |
Procedure
Step 1: Load the Plan
Open tasks/todo.md with view. Locate the next - [ ] step. If none exist, the plan is done — hand off to finishing-a-development-branch.
Step 2: Check Prerequisites
Read the task. Confirm any "depends on" notes are satisfied. If a prerequisite is missing, STOP — do not improvise around it; re-plan first.
Step 3: Execute Exactly One Task
Make the change. Resist the urge to bundle "while I'm here" cleanups. Scope discipline is the whole point of the plan.
Step 4: Verify
Invoke the verify-before-done skill. Do not consider the task complete until it has produced a Verification Results block:
Step 5: Commit and Mark Done
Then edit tasks/todo.md to flip - [ ] → - [x].
Step 6: Handle Blockers Explicitly
If a task cannot complete as planned:
- Do not improvise around it.
- Annotate the task in
tasks/todo.md:
```markdown
- [ ] Step 3: Implement API endpoints
> ⚠️ BLOCKED: Schema does not support required query. Need index or restructure Step 1. ```
- Re-plan. Update the plan. Resume from the revised version.
Step 7: Progress Updates
Every 2–3 completed tasks, post a short status:
Pitfalls
- DO NOT skip the plan order without re-planning first.
- DO NOT batch 5 tasks then verify once. Verify after each.
- DO NOT add scope mid-execution ("while I'm here…"). Log it as a follow-up; stay on plan.
- DO NOT mark a task done without a Verification Results block.
- DO NOT silently work around blockers. Annotate and re-plan.
Verification
- [ ] Every flipped
- [x]has a Verification Results block above it. - [ ] One commit per completed task (or one logical unit).
- [ ] No scope was added to the plan without explicit user agreement.
- [ ] Progress updates were posted at least every 3 tasks.
- [ ] Blockers, if any, are documented in
tasks/todo.md.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/executing-plans/SKILL.md
Popularity
- Repository stars
- 32
- Repository forks
- 12
- 7-day trend score
- 17
Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 28 Apr 2026, 6 months ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/andreaswasita/copilot-agents-dojo/executing-plans)