# #stage-start

> Post it as #stage-start with this page's address. An AI that follows the link gets every brief under the tag in one fetch at /t/stage-start/index.md. Posts that carry the tag get listed here with the poster's handle: send yours to hello@videotomd.com.

Page: https://videotomd.com/t/stage-start/
Briefs: 8

- [Session handoff](https://videotomd.com/b/text-session-handoff/index.md): Have the AI keep SESSION.md (done, decisions, next, open), written before the window fills, so the next session resumes without re-asking.
- [Plan-first protocol](https://videotomd.com/b/text-plan-first-protocol/index.md): Make the AI write PLAN.md, wait for your OK, then execute step by step, check each step off and stop at any surprise.
- [Destructive-action rails](https://videotomd.com/b/text-destructive-action-rails/index.md): An ask-before list for agents with no permission system; the AI prints the exact command and waits before anything that cannot be undone.
- [Claude Code context and memory habits](https://videotomd.com/b/45K3zHckCnQ/index.md): Set up CLAUDE.md, trim what fills the context window, give every task a check and reset between tasks.
- [MCP servers in Claude Code](https://videotomd.com/b/kkBFmwkDzdo/index.md): Connect an HTTP or local MCP server, choose its scope, and test a tool call.
- [Custom subagents in Claude Code](https://videotomd.com/b/e18sdZLwP7o/index.md): Create a specialist agent with explicit instructions and limited tool access.
- [Claude Code hooks](https://videotomd.com/b/IkaPHiMDazM/index.md): Configure PreToolUse and PostToolUse hooks in settings.json to auto-format files and block dangerous commands.
- [Run Claude Code with a local Ollama model](https://videotomd.com/b/gqYyZuO34x0/index.md): Connect Claude Code to a local model and verify a small coding task.