agentleFS
Sign inStart free
erencivrilerencivril/claude-code-failover/skills/handoff/SKILL.md

handoff

Skill1 starsChanged 34 days agoMITView on GitHub

Hand one piece of work to the fallback agent configured for the failover plugin and report what it did. Runs only when the user invokes it.

191 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use decision-mapping, setup-ts-deep-modules 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.
  • FabienDehopreSkill

    decision-mapping

    Turn a loose idea into a sequenced map of investigation tickets, then drive them to resolution one at a time.

    Also in 8 projects that use this

  • liufeng1976Skill

    setup-ts-deep-modules

    Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.

    Also in 42 projects that use this

  • AWSSkill

    to-questionnaire

    Turn a decision you can't fully answer into a questionnaire for someone else to fill in.

    Also in 93 projects that use this

  • GoogleSkill

    ask-matt

    Ask which skill or flow fits your situation. A router over the skills in this repo.

    Also in 87 projects that use this

  • RoentekSkill

    loop-me

    Grill me about specs for the workflows I want to build, within this workspace.

    Also in 51 projects that use this

  • LesaniSkill

    writing-beats

    Shape an article as a journey of beats, choose-your-own-adventure style. The user picks a starting beat from the raw material, you write only that beat, then offer options for where to pivot next, beat by beat, until the article reaches a natural end. Use when the user has raw material and wants to assemble it as a narrative rather than an argument.

    Also in 54 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 172 edited versions we read keep these.

  • 2

    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 the text above is empty, ask the user what to hand off and stop.

    line 16
  2. Distinctive:

    Do not open or review the files the agent changed unless the user asks.

    line 27

“Common” is measured: kept by at least 6 in 10 of the 172 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

Hand off to the fallback agent

The user wants this piece of work done by their configured fallback agent instead of in this session:

$ARGUMENTS

Steps

  1. If the text above is empty, ask the user what to hand off and stop.

  2. Run the handoff from the project's working directory, passing the user's text verbatim as the task. Do not rewrite, expand, or add detail to it; the only thing you may append is a list of file paths the user already named in this conversation. The script finds this session's recorded conversation by checking that the task starts with the exact text the user typed after /failover:handoff, which is why the text must not be changed; do not pass --session.

    "${CLAUDE_PLUGIN_ROOT}/scripts/handoff.sh" <<'FAILOVER_TASK'
<the user's text, verbatim>
FAILOVER_TASK

    Agent runs can take several minutes, so start the command in the background and wait for it to finish.

  3. Report what the script printed: the exit code, the files it changed, and the end of the agent's output. If the exit code is non-zero, say so and point to the log directory; do not retry on your own. Exit code 78 means no handoff command is configured: tell the user to run /failover:setup.
  4. Do not open or review the files the agent changed unless the user asks. If this session stopped on that content once, reading it back in can stop it again.
  5. Carry on with whatever part of the user's task is still open in this session.

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.

Check your setup, free