agentleFS
alexjmiller5alexjmiller5/agent-config-public/skills/afk/SKILL.md

afk

Skill0 starsChanged 42 days agoMITView on GitHub

Use when the user is leaving and wants work to continue without them - "I have to leave", "I'll be back in a few hours", "do as much as you can before you need me", "keep going while I'm gone", "get a lot done while I'm away".

19 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use fmx-respond, harness-adapters and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • karanmrnSkill

    fmx-respond

    Agent-only playbook for handling an X mention in X mode. Use on an "x-mention <request_id>" check: wake - read the stashed mention (with any in_reply_to conversation context); the direct author is the firstmate's own owner (captain) under owner-only routing, so classify it as an actionable request to act on through the normal lifecycle, a question to answer from live fleet state, or a pure acknowledgment to dismiss without replying; act autonomously (escalating only destructive/irreversible/security-sensitive work). For a request that spawns real work, acknowledge first, act, link the task with bin/fm-x-link.sh, and let the completion follow-up post on the done wake; for a question or completed action, post or preview a short public-safe reply with bin/fm-x-reply.sh; for a pure acknowledgment, call bin/fm-x-dismiss.sh. Clear the inbox file only after a successful reply or dismiss. Loaded only when X mode is enabled.

    Also in 3 projects that use this

  • karanmrnSkill

    harness-adapters

    Agent-only reference for firstmate harness operations. Use before spawning or recovering a crewmate or secondmate, handling a trust dialog, sending a harness-specific skill invocation, interrupting or exiting an agent, resuming an exited agent, or verifying a new harness adapter. Contains verified facts for claude, codex, opencode, and pi.

    Also in 3 projects that use this

  • Hugging FaceSkill

    simplify

    Refactor code after tests pass. The "Refactor" phase of Red-Green-Refactor.

    Also in 3 projects that use this

  • GoogleSkill

    prototype

    Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.

    Also in 5 projects that use this

  • GoogleSkill

    improve-codebase-architecture

    Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

    Also in 4 projects that use this

  • MicrosoftSkill

    writing-for-agents

    Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.

    Also in 3 projects that use this

  • +3 more from karanmrn
  • +3 more from google

The file

We split this skill into the rules it gives an agent

10 rules. 0 are common, 8 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 18 edited versions we read keep these.

  • 8

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Every turn you end on a question now costs hours.

    line 8
  2. Very specific:

    Run quota-axi --provider <yours> (the quota skill): a local read, safe anywhere.

    line 13
  3. Distinctive:

    do the most valuable work first, and commit more often.

    line 19
  4. Distinctive:

    before it runs out, port the session to another agent with a session-switching skill and tell the new one to continue.

    line 20
  5. Distinctive:

    Commit and push each finished piece as your rules allow, so a cutoff loses nothing.

    line 36
  6. Distinctive:

    Never end the turn with a question while unblocked work remains.

    line 39
  7. Distinctive:

    Before handing back, stop what you started: background commands, watchers, servers.

    line 40
  8. Very specific:

    When nothing doable remains, the final message uses the catch-up format (Done, In progress, Needs you, Remaining, Loose ends).

    line 45
  9. Distinctive:

    Every assumption you made goes under Needs you, so the user can confirm or reverse it.

    line 47
  10. Distinctive:

    If the harness can send a push notification, send one line: done, plus the number of decisions waiting.

    line 49

“Common” is measured: kept by at least 6 in 10 of the 18 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

AFK: keep working while the user is away

Every turn you end on a question now costs hours. Work until nothing you can do remains, then hand back once.

Start, in this turn

  1. Run quota-axi --provider <yours> (the quota skill): a local read, safe anywhere.
  2. One line to the user: what you will work through, and your headroom from step 1 ("Opus: 38% of the weekly window left, resets Mon"). A session that hits its limit stops dead for the rest of the absence, so if the window will not last:
    • do the most valuable work first, and commit more often;
    • before it runs out, port the session to another agent with a session-switching skill and tell the new one to continue.
  3. Split the remaining work into can do now and needs the user.

While away

  • Needs the user:

    • approvals your rules require (deploys, deletes, publishing, messages to people, money);
    • sign-ins and credentials;
    • physical steps;
    • calls only they can make (names, taste, priorities).

    Park each with options and your recommendation, then work around it.

  • A decision blocking later work, with a default that is cheap to undo: take the default, note it as an assumption, keep going.
  • Commit and push each finished piece as your rules allow, so a cutoff loses nothing.
  • Recheck headroom between chunks of work.
  • Never end the turn with a question while unblocked work remains.
  • Before handing back, stop what you started: background commands, watchers, servers. Remove your build output and temp files.

Hand back

  • When nothing doable remains, the final message uses the catch-up format (Done, In progress, Needs you, Remaining, Loose ends).
  • Every assumption you made goes under Needs you, so the user can confirm or reverse it.
  • If the harness can send a push notification, send one line: done, plus the number of decisions waiting.

Common mistakes

MistakeInstead
Ending on the first questionPark it, keep working around it
The session hits its usage limit mid-absenceCheck at start and between chunks; switch agents before it runs out
Deciding names, taste or priorities for the userPark with a recommendation
An irreversible step "to save them time"Park it; it waits for their approval
A free-form final messageThe catch-up format, assumptions under Needs you

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.