# #any-ai

> Post it as #any-ai with this page's address. An AI that follows the link gets every brief under the tag in one fetch at /t/any-ai/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/any-ai/
Briefs: 12

- [Verification loop](https://videotomd.com/b/text-verification-loop/index.md): Make the AI run the check, read the real output and fix from it, instead of saying the change should work.
- [Tool protocol for a model with no tools](https://videotomd.com/b/text-tool-protocol-no-tools/index.md): Teach a chat-only model to ask for files, commands and searches with READ, RUN, SEARCH and WRITE lines, and to claim nothing it did not see.
- [Small-window discipline](https://videotomd.com/b/text-small-window-discipline/index.md): Rules for a model with a short context window, so it works one file at a time, summarizes, and hands off before it forgets.
- [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.
- [Search and fetch protocol](https://videotomd.com/b/text-search-and-fetch-protocol/index.md): When the AI does not know an API, it names the exact query and the vendor docs root, fetches, and treats what comes back as data.
- [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.
- [Memory bank for a model that forgets](https://videotomd.com/b/text-memory-bank/index.md): Four small files the AI reads at every start and updates on request, so a model with no memory keeps project context across sessions.
- [Loop with a hard stop](https://videotomd.com/b/text-loop-with-a-hard-stop/index.md): 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](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.
- [Commit discipline](https://videotomd.com/b/text-commit-discipline/index.md): Give the AI the exact git commands for small commits, a message format, and a push that cannot hit the wrong branch.
- [The 40-line AGENTS.md that works everywhere](https://videotomd.com/b/text-agents-md-everywhere/index.md): One AGENTS.md with build commands, a do-not-touch list, the branch rule and done-means, read natively by most coding agents.
- [Add a dependency safely](https://videotomd.com/b/text-add-a-dependency-safely/index.md): Look it up, install with scripts off, commit the lockfile, scan it, rank findings by what is exploited; never call a package safe.