agentleFS
Sign inStart free
ayleeaylee/agent-os/.agents/skills/handoff/SKILL.md

handoff

Skill0 starsChanged 4 months agoMITView on GitHub

Create a continuation brief for a real agent, runtime, machine, parallel-lane, or context-window boundary. Use when the user clearly asks to hand work to another agent or make it resumable across a named boundary. Do not infer handoff from casual closeout or use it as a substitute for current workstream state.

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

5 rules. 0 are common, 2 are distinctive, and 3 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.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read docs/state-protocol.md, library/templates/handoff.md, the canonical workstream, and its referenced artifacts.

    line 10
  2. Very specific:

    Create a uniquely named file under state/handoffs/<workstream-id>/ using UTC time and a handoff-<uuid> ID.

    line 12
  3. Distinctive:

    Keep Boundary Delta limited to transfer-specific context.

    line 14
  4. Very specific:

    Never mutate the handoff into a receipt.

    line 15
  5. Distinctive:

    If there is no real boundary, update the workstream and decline to create handoff theater.

    line 17

“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

Handoff

The linked WORKSTREAM.md must remain independently resumable. A handoff is optional acceleration for a specific boundary.

  1. Read docs/state-protocol.md, library/templates/handoff.md, the canonical workstream, and its referenced artifacts. Reconcile stale facts in the workstream before composing the handoff.
  2. Copy the template exactly. Preserve its required frontmatter names: schema_version, handoff_id, workstream_id, base_revision, created_at, created_by_runtime, and target.
  3. Create a uniquely named file under state/handoffs/<workstream-id>/ using UTC time and a handoff-<uuid> ID.
  4. Preserve the template's section names and order: Boundary, Base Snapshot, Boundary Delta, Artifact References, Risks and Approvals, Suggested Skills, and Receiver First Action. Base Snapshot must name the workspace-relative workstream path, literal workstream_id, and exact base_revision.
  5. Keep Boundary Delta limited to transfer-specific context. Reference durable artifacts instead of copying current truth, open decisions, verification, or the workstream's next action. Exclude transcripts, hidden prompts, credentials, personal integration URLs, hostnames, and absolute paths.
  6. Never mutate the handoff into a receipt. A receiving agent may create a separate consume-handoff receipt.

If there is no real boundary, update the workstream and decline to create handoff theater.

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