# executing-plans

> Claude/Codex skill by [@obra](https://omgskills.com/library/obra/index.md) · 308k stars · 261k installs · Updated 2026-10-23

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

Tags: ai, brainstorming, coding, obra, sdlc, skills, subagent-driven-development, superpowers

## Install

```sh
git clone https://github.com/obra/superpowers /tmp/superpowers && ln -s /tmp/superpowers/skills/executing-plans ~/.claude/skills/executing-plans
```

## From README

Executing Plans Execute the plan yourself, task by task, in this session: no implementer subagent per task, no reviewer per task. One fresh-context review of the whole branch at the end. Why inline: Subagent-driven development pays for a fresh implementer and a fresh reviewer on every task, each re-reading the codebase from zero. Inline execution pays for one context (yours) plus one reviewer at the end. What it gives up is a fresh context per task and a second pair of eyes per task. This skill keeps what those two things bought, by other means: the brief is the spec, the ledger is your memory, TDD is the per-task gate, and the final reviewer is the second pair of eyes. Core principle: The plan already did the thinking. Execute it exactly, prove each step with a test you watched fail and then pass, and leave a record that survives your own forgetting. Narration: between tool calls, narrate at most one short line — the ledger and the tool results carry the record.

## Links

- HTML page: https://omgskills.com/library/obra/superpowers/executing-plans/
- GitHub: https://github.com/obra/superpowers
- Author: [@obra](https://omgskills.com/library/obra/index.md)

## More from this repo

- [systematic-debugging](https://omgskills.com/library/obra/superpowers/systematic-debugging/index.md) — Used when encountering any bug, test failure, or unexpected behavior, before proposing fixes
   - [@obra](https://omgskills.com/library/obra/index.md) · 317k stars
- [subagent-driven-development](https://omgskills.com/library/obra/superpowers/subagent-driven-development/index.md) — Used when executing implementation plans with independent tasks in the current session
   - [@obra](https://omgskills.com/library/obra/index.md) · 308k stars
- [writing-skills](https://omgskills.com/library/obra/superpowers/writing-skills/index.md) — Used when creating new skills, editing existing skills, or verifying skills work before deployment
   - [@obra](https://omgskills.com/library/obra/index.md) · 308k stars
