/TAG

#agents

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

Verification loop Make the AI run the check, read the real output and fix from it, instead of saying the change should work.
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.
Commit discipline Give the AI the exact git commands for small commits, a message format, and a push that cannot hit the wrong branch.
Edit files with LM Studio Bionic Create a project, select a model, and check its file changes.
Keep Agent Actions Within Their Deadline Limit each model call and switch to a deterministic policy when the response cannot supply usable actions.
Cursor Projects agent coordinator Coordinates autonomous multi-agent coding tasks across cloud and local machines with persistent threads and event triggers.
Google Antigravity 2.0 agent platform Dispatches and manages parallel AI agents to plan, code, debug, and run automated tasks.
Antigravity Remote Control Monitor and steer coding agents across machines from a mobile device without syncing local build environments.
Connect n8n agents and workflows Build an agent, expose a workflow tool, and call the agent from another workflow.
Your first AI agent in n8n Build Q&A ingestion and retrieval workflows, then test answers against stored records.