Implementation Executor

Executing plans

by obra · MIT license · ★ 289,792 on GitHub · updated Sep 20

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

---
name: executing-plans
description: Use when you have a written implementation plan to execute in a separate session with review checkpoints
---

# 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 (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

Overview

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

The SKILL.md below is the copy AgentAlley read and checked. The repo has changed it since; the other files are from commit 5bf4e78.

Manual install (npx, ZIP)

Claude Codenpx skills add obra/superpowers --skill executing-plans -g -a claude-code

Claude Code (manual)

mkdir -p ~/.claude/skills && curl -sL https://codeload.github.com/obra/superpowers/tar.gz/5bf4e7801107 \
  | tar -xz -C ~/.claude/skills --strip-components=2 superpowers-5bf4e7801107/skills/executing-plans

Windows (PowerShell)

New-Item -ItemType Directory -Force "$HOME\.claude\skills" | Out-Null; Invoke-WebRequest "https://m.agentalley.io/zip/ec666bfcf625df944717/executing-plans.zip" -OutFile "$env:TEMP\executing-plans.zip"; Expand-Archive "$env:TEMP\executing-plans.zip" -DestinationPath "$HOME\.claude\skills" -Force

Claude.ai / desktopDownload the ZIP and upload it under Settings → Capabilities → Skills.

Codex, Cursor, other agentsPoint them at SKILL.md. The other files are plain text.

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

SKILL.md19.9 KB
scripts/2 files · 2.6 KB

Read the files here

obra/5bf4e783 files

SKILL.md19.9 KB

SKILL.md

Show the full text65 lines

executing-plans/SKILL.md65 lines · 2.3 KB

PreviewCode

Outline

RawView on GitHub

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 (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

Ensure an isolated workspace: use superpowers:using-git-worktrees to create one or verify the existing one
Read plan file
Review critically - identify any questions or concerns about the plan
If concerns: Raise them with your human partner before starting
If no concerns: Create todos for the plan items and proceed

Step 2: Execute Tasks

For each task:

Mark as in_progress
Follow each step exactly (plan has bite-sized steps)
Run verifications as specified
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

1	---
2	name: executing-plans
3	description: Use when you have a written implementation plan to execute in a separate session with review checkpoints
4	---
5
6	# Executing Plans
7
8	## Overview
9
10	Load plan, review critically, execute all tasks, report when complete.
11
12	Announce at start: "I'm using the executing-plans skill to implement this plan."
13
14	Note: Tell your human partner that Superpowers works much better with access to subagents (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.
15
16	## The Process
17
18	### Step 1: Load and Review Plan
19	1. Ensure an isolated workspace: use superpowers:using-git-worktrees to create one or verify the existing one
20	2. Read plan file
21	3. Review critically - identify any questions or concerns about the plan
22	4. If concerns: Raise them with your human partner before starting
23	5. If no concerns: Create todos for the plan items and proceed
24
25	### Step 2: Execute Tasks
26
27	For each task:
28	1. Mark as in_progress
29	2. Follow each step exactly (plan has bite-sized steps)
30	3. Run verifications as specified
31	4. Mark as completed
32
33	### Step 3: Complete Development
34
35	After all tasks complete and verified:
36	- Announce: "I'm using the finishing-a-development-branch skill to complete this work."
37	- REQUIRED SUB-SKILL: Use superpowers:finishing-a-development-branch
38	- Follow that skill to verify tests, present options, execute choice
39
40	## When to Stop and Ask for Help
41
42	STOP executing immediately when:
43	- Hit a blocker (missing dependency, test fails, instruction unclear)
44	- Plan has critical gaps preventing starting
45	- You don't understand an instruction
46	- Verification fails repeatedly
47
48	Ask for clarification rather than guessing.
49
50	## When to Revisit Earlier Steps
51
52	Return to Review (Step 1) when:
53	- Partner updates the plan based on your feedback
54	- Fundamental approach needs rethinking
55
56	Don't force through blockers - stop and ask.
57
58	## Remember
59	- Review plan critically first
60	- Follow plan steps exactly
61	- Don't skip verifications
62	- Reference skills when plan says to
63	- Stop when blocked, don't guess
64	- Never start implementation on main/master branch without explicit user consent
65