/TAG

#stage-build

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

Session handoff 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 Make the AI write PLAN.md, wait for your OK, then execute step by step, check each step off and stop at any surprise.
Loop with a hard stop For loops nobody watches: the runner caps turns and spend, done is an exit code, and the AI prints LOOP STOP and hands back on churn.
Destructive-action rails An ask-before list for agents with no permission system; the AI prints the exact command and waits before anything that cannot be undone.
Add a dependency safely Look it up, install with scripts off, commit the lockfile, scan it, rank findings by what is exploited; never call a package safe.
Reverse engineer a feature with REA, evidence first Point your agent at an app, a bundle or a binary, get how a feature works with the evidence behind it, then build your own version.
Claude Code context and memory habits Set up CLAUDE.md, trim what fills the context window, give every task a check and reset between tasks.
MCP servers in Claude Code Connect an HTTP or local MCP server, choose its scope, and test a tool call.
Custom subagents in Claude Code Create a specialist agent with explicit instructions and limited tool access.
Claude Code hooks Configure PreToolUse and PostToolUse hooks in settings.json to auto-format files and block dangerous commands.
Run Claude Code with a local Ollama model Connect Claude Code to a local model and verify a small coding task.