Skip to content

/optim-plans

MUST USE when a user asks to plan, brainstorm, design, scope, review, or evaluate a repo change before implementation; do not use for direct implementation-only requests, factual/explanation questions, trivial operations, or explicit no-plan requests.

shell
$ npx -y skills add Optim-Agent/optim-plans --skill optim-plans --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
  • You can call itInvoke it directly when you want it.
  • Slash command/optim-plans
How auto-invocation works

Context preview

The summary Claude sees to decide when to auto-load this skill.

MUST USE when a user asks to plan, brainstorm, design, scope, review, or evaluate a repo change before implementation; do not use for direct implementation-only requests, factual/explanation questions, trivial operations, or explicit no-plan requests.
Ships withoptim-plans

Human-in-the-loop planning plugin for Claude and Codex: turn ideas into reviewed Markdown plans, record decisions, enforce explicit execution gates, and provide tested controller primitives for safer agent workflows.

Get the whole plugin, auto-invoked
Stats
306
Stars
0
Views
1
Forks
Active
Maintenance
Python
Language
MIT
License
3h ago
Last commit
12d ago
Created

Repo: Optim-Agent/optim-plans