Executing Plans
Run a written implementation plan in bounded batches with verification, human checkpoints, and a forced finish workflow when all tasks are done.
Overview
Executing-plans is an agent skill most often used in Build (also Ship) that implements written plans in review checkpoints batches and requires finishing-a-development-branch when development is complete.
Install
npx skills add https://github.com/sickn33/antigravity-awesome-skills --skill executing-plansWhat is this skill?
- Loads plan, critical review, and TodoWrite before any implementation
- Default batch size of first 3 tasks with in_progress → completed discipline
- Runs plan-specified verifications each task and reports with “Ready for feedback.”
- Iterates batches from human feedback until the plan is complete
- Hard gate: invokes finishing-a-development-branch after all tasks verify
- Default first batch: 3 tasks
- 5-step process from load plan through complete development
Adoption & trust: 530 installs on skills.sh; 40.1k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You have a written implementation plan but the agent either skips steps or barrels through the entire spec without verification or your review.
Who is it for?
Solo builders executing Superpowers or similar multi-step plan files in a fresh session with architect-style review between batches.
Skip if: Exploratory spikes with no plan file, one-line fixes, or work where you refuse checkpoint pauses between task groups.
When should I use this skill?
Use when you have a written implementation plan to execute in a separate session with review checkpoints.
What do I get? / Deliverables
Plan tasks complete in verified batches with feedback loops, then control passes to finishing-a-development-branch for tests and merge-ready completion.
- Completed plan tasks with verification logs
- Batch progress reports ending with Ready for feedback
- Handoff to branch completion workflow
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Plans are executed during active product construction, so Build PM is the canonical shelf even though verification spans Ship. PM covers turning plan tasks into tracked todos, batch execution, and explicit pause points for partner review—not one-shot codegen.
Where it fits
First batch implements three UI tasks from the plan with component tests the plan lists.
Agent marks API tasks in progress, runs curl or unit checks specified in the plan, then stops for feedback.
Final batches only land when verifications green, then finishing-a-development-branch owns full test suite and merge options.
How it compares
Use after writing-plans—not instead of ad-hoc “just implement everything” agent sessions.
Common Questions / FAQ
Who is executing-plans for?
Developers using community Superpowers workflows who need disciplined, verifiable plan execution with human review gates.
When should I use executing-plans?
In Build when a plan file exists; during Ship when batches include test verification; whenever you start a session whose sole job is to implement an approved plan.
Is executing-plans safe to install?
It drives code changes and subprocess verifications from your plan; review the Security Audits panel on this page and keep plans scoped to commands you trust.
Workflow Chain
Requires first: writing plans
Then invoke: finishing a development branch
SKILL.md
READMESKILL.md - Executing Plans
# Executing Plans ## Overview Load plan, review critically, execute tasks in batches, report for review between batches. **Core principle:** Batch execution with checkpoints for architect review. **Announce at start:** "I'm using the executing-plans skill to implement this plan." ## The Process ### Step 1: Load and Review Plan 1. Read plan file 2. Review critically - identify any questions or concerns about the plan 3. If concerns: Raise them with your human partner before starting 4. If no concerns: Create TodoWrite and proceed ### Step 2: Execute Batch **Default: First 3 tasks** For each task: 1. Mark as in_progress 2. Follow each step exactly (plan has bite-sized steps) 3. Run verifications as specified 4. Mark as completed ### Step 3: Report When batch complete: - Show what was implemented - Show verification output - Say: "Ready for feedback." ### Step 4: Continue Based on feedback: - Apply changes if needed - Execute next batch - Repeat until complete ### Step 5: Complete Development After all tasks complete and verified: - Announce: "I'm using the finishing-a-development-branch skill to complete this work." - **REQUIRED SUB-SKILL:** Use superpowers:finishing-a-development-branch - Follow that skill to verify tests, present options, execute choice ## When to Stop and Ask for Help **STOP executing immediately when:** - Hit a blocker mid-batch (missing dependency, test fails, instruction unclear) - Plan has critical gaps preventing starting - You don't understand an instruction - Verification fails repeatedly **Ask for clarification rather than guessing.** ## When to Revisit Earlier Steps **Return to Review (Step 1) when:** - Partner updates the plan based on your feedback - Fundamental approach needs rethinking **Don't force through blockers** - stop and ask. ## Remember - Review plan critically first - Follow plan steps exactly - Don't skip verifications - Reference skills when plan says to - Between batches: just report and wait - Stop when blocked, don't guess ## When to Use This skill is applicable to execute the workflow or actions described in the overview. ## Limitations - Use this skill only when the task clearly matches the scope described above. - Do not treat the output as a substitute for environment-specific validation, testing, or expert review. - Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.