agentleFS
OHOKAYYEAHOHOKAYYEAH/claude-skills/skills/wait/SKILL.md

wait

Skill1 starsChanged 33 days agoMITView on GitHub

Park the session as waiting on external input, and nothing else. The done-rename.sh UserPromptSubmit hook prefixes the session title with \"[WAIT]\" and blocks the turn instantly (no LLM turn), because parking is a move-on moment. Use when a session is in progress but blocked on a **non-code answer from outside**: a decision, approval, or information you are waiting on from someone or something else (a stakeholder review, an approval, an upstream answer) before it can move forward. NOT for code/CI/build/deploy blockers. Strips any existing [DONE]/[WAIT]/[TODO] tag first, so states transition cleanly. Sibling of /done.

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

/wait parks the session as blocked on a non-code answer from outside (a decision, approval, or info you're waiting on from someone or something else — not a code/CI/deploy blocker) and does nothing else. In normal operation you will never read this body: the done-rename.sh UserPromptSubmit hook intercepts /wait, prefixes the session title with [WAIT] (stripping any existing lifecycle tag first, so [DONE] X or a bare X both become [WAIT] X), and blocks the turn — no LLM turn, no report. That instant park is the whole point. The tag set: no prefix = active, [DONE] = finished and archived, [WAIT] = blocked on outside input.

Fallback — if you ARE executing this body, the hook did not block (settings.json not read, hooks disabled, or the prompt leaked through with different args). Then: emit a single clean one-line confirmation that the session is parked as [WAIT], do nothing else (no report, no codify), and flag the wiring — check the UserPromptSubmit entry in your settings.json and the done-rename.sh script it points at (see substrate/hooks/README.md in this repo for the install).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.