executing-plans

executing-plans is a Claude skill by obra that use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available.

Updated 2026-10-10

What is executing-plans?

executing-plans is a Claude skill by obra that use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available. It is listed under Engineering practice and has 228,600 installs.

TypeClaude skill
Authorobra
Repositoryobra/superpowers
Popularity228,600 installs
CategoryEngineering practice
SecurityLow risk (100/100)
Rank#118 of 1,262 Claude skills; #26 in Engineering practice
SKILL.md length373 lines
LicenseMIT
Last commit2026-10-10
Stars this week+3,625

Is executing-plans safe to install?

executing-plans scores 100/100 on the MCPMods security check: Low risk. No checks raised a concern. It passed 9 of 9 checks.

Skill results come from a static scan of its SKILL.md for instruction overrides, hidden actions, risky commands and credential access.

CheckResult
No instruction-override phrasesPass
No hidden actionsPass
No pipe-to-shell installersPass
No obfuscated codePass
No destructive commandsPass
Doesn't ask for keys or credentialsPass
No network requestsPass
No shell commandsPass
Installs no packagesPass

How do I install executing-plans?

  1. Install with the skills CLI. Works for Claude Code and other agents that read skills.
    npx skills add https://github.com/obra/superpowers --skill executing-plans
  2. Or copy it by hand. Claude Code loads any folder with a SKILL.md from ~/.claude/skills.
    git clone https://github.com/obra/superpowers
    cp -r superpowers/skills/executing-plans ~/.claude/skills/executing-plans
  3. Use it. Claude loads the skill when a task matches its description. You can also name it in your prompt.
    Use the executing-plans skill to …

Or ask Claude to set it up

Paste this into Claude Code and it installs executing-plans for you:

Install the "executing-plans" skill from https://github.com/obra/superpowers/tree/main/skills/executing-plans into ~/.claude/skills, then tell me in one line what it does.

More from obra/superpowers

This repository has at least 9 Claude skills on MCPMods.

  • brainstorming: You MUST use this before any creative work - creating features, building components, adding functionality, modifying beh (Low risk)
  • systematic-debugging: Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes (Low risk)
  • writing-plans: Use when you have a spec or requirements for a multi-step task, before touching code (Low risk)
  • using-superpowers: Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY respo (Low risk)
  • requesting-code-review: Use when completing tasks, implementing major features, or before merging to verify work meets requirements (Low risk)
  • test-driven-development: Use when implementing any feature or bugfix, before writing implementation code (Low risk)
  • verification-before-completion: Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verifi (Low risk)
  • subagent-driven-development: Use when executing implementation plans with independent tasks in the current session (Low risk)