Catalog
obra/executing-plans

obra

executing-plans

Use when you have a written implementation plan to execute in a separate session with review checkpoints

global
New~639
v1.1Saved Jun 28, 2026

Executing Plans

Overview

Load plan, review critically, execute all tasks, report when complete.

Announce at start: "I'm using the executing-plans skill to implement this plan."

Note: Tell your human partner that Superpowers works much better with access to subagents. The quality of its work will be significantly higher if run on a platform with subagent support (Claude Code, Codex CLI, Codex App, Copilot CLI, and Gemini CLI all qualify; see the per-platform tool refs in ../using-superpowers/references/). If subagents are available, use superpowers:subagent-driven-development instead of this skill.

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 todos for the plan items and proceed

Step 2: Execute 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: 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 (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
  • Stop when blocked, don't guess
  • Never start implementation on main/master branch without explicit user consent

Integration

Required workflow skills:

  • superpowers:using-git-worktrees - Ensures isolated workspace (creates one or verifies existing)
  • superpowers:writing-plans - Creates the plan this skill executes
  • superpowers:finishing-a-development-branch - Complete development after all tasks
Files1
1 files · 1.0 KB

Select a file to preview

Overall Score

82/100

Grade

B

Good

Safety

85

Quality

82

Clarity

85

Completeness

75

Summary

This skill guides an AI agent through executing a pre-written implementation plan with critical checkpoints. It establishes a structured workflow (load plan → review → execute → verify → hand off to finishing skill) with safety guardrails that require the agent to stop at blockers, ask for clarification, and escalate to a finishing skill for final steps. The skill emphasizes isolation via git worktrees and recommends subagent-driven development when available.

Detected Capabilities

file read (plan file)task execution (following plan steps)code verification (running tests/verifications)git operations (via referenced git-worktrees skill)skill invocation (references finishing-a-development-branch skill)

Trigger Keywords

Phrases that MCP clients use to match this skill to user intent.

execute implementation planrun planned tasksfollow development planimplement feature planexecute plan with checkpoints

Use Cases

  • Execute a detailed development plan with verification checkpoints
  • Implement a complex feature broken into bite-sized tasks
  • Run a planned refactoring with critical review gates
  • Complete a multi-step implementation with task tracking and handoff
  • Execute a plan on a feature branch with mandatory test verification

Quality Notes

  • Clear step-by-step workflow with explicit decision points and stop conditions
  • Safety guardrails are well-defined (blocker detection, mandatory clarification, no guessing)
  • Explicit requirement to use git worktrees ensures isolation from main branch
  • Integration points clearly documented (links to three complementary skills)
  • References subagent-driven development as higher-quality alternative when available
  • Instructions on when to stop and escalate are actionable and non-negotiable
  • Scope is tightly constrained to plan execution, not plan creation
  • The skill correctly defers to finishing-a-development-branch for final steps, avoiding scope creep
Model: claude-haiku-4-5-20251001Analyzed: Jun 28, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Version History

  1. v1.1

    Content updated

    ✦ AIClarifies platform support for subagents (adds CLI variants), changes step 4 instruction from TodoWrite to generic todos, and softens git-worktrees requirement language.

    2026-06-28

    Latest
  2. v1.0

    2026-05-02

    Initial version

Use obra/executing-plans in your dev environment

Command Palette

Search for a command to run...