/plan
Use before starting any non-trivial task.
$ npx -y skills add yeaight7/agent-powerups --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/plan
Context preview
What this command does when you run it.
Use before starting any non-trivial task.
Command definition
plan.mdplan
Use before starting any non-trivial task.
Steps:
1. Re-read the user request in full. Identify the goal, constraints, and what "done" means. 2. Map affected areas: run `git status --short` and `apx list` to see what exists. 3. List the files most likely to change. For each, read its current state with the Read tool. 4. Write a numbered step list — small enough that each step is one logical change. 5. Identify risks: external dependencies, breaking changes, missing context. 6. Present the plan to the user and wait for approval before implementing.
Do not write code or modify files during planning.
Curated power-ups for coding agents: skills, slash commands, MCP configs, hooks, AGENTS.md templates, and workflows for serious software engineering. Claude Code, Codex, Antigravity CLI, Cursor and more
Repo: yeaight7/agent-powerups
Other commands on agent-powerups.
- /bug-check
Run automated tests and build checks first, then agent code review. For each bug found, propose or document a regression test.
Open command - /build-fix
Use when a build, type check, or test suite is failing and needs to be unblocked with a minimal change.
Open command - /debug
Use when a bug needs systematic diagnosis before a fix is attempted.
Open command - /doctor
Use to diagnose environment, tooling, and Agent Powerups setup problems.
Open command - /implement
Use to turn a spec or user request into working, tested code.
Open command - /mcp-check
Use to check MCP server prerequisites before activating or using a server.
Open command