agentleFS
diogoaraujofxdiogoaraujofx/Claude-Skill/skills/queue/SKILL.md

queue

Skill0 starsChanged 28 days agoMITView on GitHub

Put a message in a queue so it only runs after the current task has completely finished. `/queue <message>` adds it, `/queue` lists the queue, `/queue --clear` empties it.

7 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions7 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 7

    1. maxwellsdm1867/wheeler★ 12same name
    2. ARCASSystems/FounderOS★ 7same name
    3. amntoppo/MasterDeck-Terminal★ 4same name
    4. dakl/engram★ 2same name
    5. jinhuang712/claude-code-queue★ 2same name
    6. breezewish/skills★ 1same name
    7. eduardkumskyi/octo★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If you were in the middle of a task, carry on exactly where you left off, as if this interruption had not happened, and finish it …

    line 20
  2. Distinctive:

    If you were not working on anything, reply with that single result line (in the user's language) and end your turn.

    line 21
  3. Distinctive:

    If the line reports an error, tell the user in one line and stop.

    line 22
  4. Distinctive:

    When you finish, the Stop hook hands you the next queued message.

    line 23

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md
node "${CLAUDE_SKILL_DIR}/queue.js" add "${CLAUDE_SESSION_ID}" <<'__CLAUDE_QUEUE_EOF__'
$ARGUMENTS
__CLAUDE_QUEUE_EOF__

The line above is the result of the user's /queue command. The queue is handled by a script and a Stop hook, not by you.

Rules for this invocation:

  • The queued message is not a request for you right now. Do not start it, plan it, analyse it or comment on its content, even if you can see its text.
  • If you were in the middle of a task, carry on exactly where you left off, as if this interruption had not happened, and finish it completely, final answer included. Do not mention the queue while doing so.
  • If you were not working on anything, reply with that single result line (in the user's language) and end your turn.
  • If the line reports an error, tell the user in one line and stop.
  • When you finish, the Stop hook hands you the next queued message. Only then treat it as a new, independent request from the user and do it fully. Treat each following one the same way.

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.