Agent0 is an AI agent framework built on Obsidian and Claude Code. It gives you 7 specialized AI agents powered by 83 reusable skills, with built-in governance, persistent memory, and a vault that catches every idea and ships the ones that matter.

Do I need to know how to code to use Agent0?

No. The Starter tier uses copy-paste prompts with step-by-step instructions. The Pro tier runs one command. The Custom tier is fully set up for you.

How is Agent0 different from other AI agent frameworks?

Agent0 runs on Obsidian and Claude Code with your data staying local. No hosted servers, no monthly infrastructure costs. The reflect/evolve layer (seeing your thinking patterns over time) is something no other framework offers.

Home/Skills/dev/Executing Plans

devDevelopment

/executing-plans

Executing Plans

Load the plan, review it critically, execute each task, verify, hand off to branch-finish.

Used by 1 agent

Axon

What it does

Executes a written implementation plan with review checkpoints at each step. Reads the plan, raises concerns before starting, creates a todo list, runs each task with its verification, and stops on blockers instead of guessing. Ends by handing off to `finishing-a-development-branch`.

Use it when a plan from `writing-plans` is ready and a fresh session should ship it. Especially valuable in subagent-less environments where linear execution is the only path. If subagents are available, prefer `subagent-driven-development` for parallel workstreams.

Outputs commits against the plan, a verified build at the end, and a branch ready for merge or PR. Pairs with `writing-plans` (the upstream planning skill) and `finishing-a-development-branch` (the downstream merge step).

Build your second brain

Run /executing-plans with your agents.

This skill ships with Agent0 Starter, plus 82 others. Axon runs it from day one.

Found an error? Fix it on GitHub