Executing Plans

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

Security Scan

The skill's instructions and requirements are consistent with its stated purpose (automating execution of a written implementation plan), but the runtime instructions give the agent broad authority to read a plan and carry out whatever steps it contains — so you should review the plan and control execution context before use.

Purpose & Capability

Name and description match the runtime instructions: the skill is explicitly about loading a plan, reviewing it, and executing tasks. The declared dependencies on other workflow skills (git worktrees, plan authoring, finishing branches) are coherent with the goal of executing development plans.

Instruction Scope

SKILL.md tells the agent to read a plan file, review it, and then "execute all tasks" and run verifications. That behavior is expected for an execution skill, but the instructions do not constrain which file paths to read or which commands the plan may run — the agent could therefore run arbitrary commands or modify files if the plan directs it. The skill does instruct to stop on blockers and to avoid acting on main/master without consent, which are useful safeguards.

Install Mechanism

Instruction-only skill with no install spec and no code files. This minimizes disk-write/installation risk.

Credentials

The skill requests no environment variables, credentials, or config paths. It does refer to external subagent platforms (Claude Code, Codex) and other skills but does not ask for unrelated secrets or broad system credentials.

Persistence & Privilege

always is false and the skill does not request persistent presence or elevated platform privileges. It does require other workflow skills to be present, which is normal for a coordinated development workflow.

Assessment

This skill will attempt to read a plan file and then carry out whatever steps are written there — including running commands or editing files — so only use it when: (1) you trust the plan's contents and its origin, (2) you have reviewed the plan yourself before execution, and (3) you run it in an isolated workspace (the skill recommends using the superpowers:using-git-worktrees skill). Before installing/using: ensure the agent prompts you for approval before any destructive or network-exfiltrating steps, avoid running it against main/master branches, and prefer disabling autonomous invocation or requiring manual confirmation for high-risk actions if your platform allows that. If you need stronger assurance, ask the skill author to specify exact file path handling and explicit authorization prompts for command execution.

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 (such as Claude Code or Codex). 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 TodoWrite 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 - REQUIRED: Set up isolated workspace before starting
• superpowers:writing-plans - Creates the plan this skill executes
• superpowers:finishing-a-development-branch - Complete development after all tasks