agentleFS
lynchypinlynchypin/project-onboard/skills/handoff/SKILL.md

handoff

Skill0 starsChanged 3 months agoMITView on GitHub

Compact the current conversation into a handoff document a fresh session can read to pick up the work. Use at a ticket boundary before /clear, or whenever the context window has grown large and the live thread would otherwise be lost.

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

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 172 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    Write it at a ticket boundary before /clear, or any time the context window has grown large enough that the next step deserves a fresh one.

    line 13
  2. Distinctive:

    Write the live thread — the reasoning that exists only in this conversation.

    line 51
  3. Distinctive:

    Write to the temp dir and report the full path to the user.

    line 56
  4. Distinctive:

    Keep the document to the live thread.

    line 67

“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

.agent/state.json and the map carry what has been settled. Neither carries the live thread — what is in flight right now, why this approach and not the other one, what was just tried and rejected. That is what compaction loses and what this document preserves.

Write it at a ticket boundary before /clear, or any time the context window has grown large enough that the next step deserves a fresh one.

Where it goes

The OS temporary directory — $TMPDIR on macOS, /tmp otherwise. Never the workspace.

A handoff is scaffolding for one session gap, not a project artifact. In the workspace it would become a third thing to keep in sync with the map and state.json, and would go stale the moment it was read.

Name it handoff-<ticket-or-topic>.md and give the user the full path so the next session can be pointed at it.

What it carries

  • The live thread — what is in flight and why, in the conversation's own terms. What was tried, what was ruled out, what the next concrete step is.
  • Suggested skills — which skills the next session should reach for.
  • References, not copies — link the map, spec, ADRs, tickets, commits, and diffs by path or URL. Everything already written down stays where it is; the handoff points at it.
  • Open questions — anything the user still owes an answer on.

Anything already captured in the map, a spec, an ADR, a ticket, a commit message, or a diff belongs in the references list, not the body. Copying it in creates a second copy that immediately starts drifting from the first.

Redaction

Strip API keys, tokens, passwords, connection strings, and personal data before writing. The temp directory is not a secret store.

Process

  1. Identify the current ticket and phase from .agent/state.json.
  2. Write the live thread — the reasoning that exists only in this conversation.
  3. List references by path or URL.
  4. Name the suggested skills for the next session.
  5. Redact secrets.
  6. Write to the temp dir and report the full path to the user.

Relationship to state.json

Complementary, not a replacement. state.json stays the machine-readable resume point the SessionStart hook reads automatically; the handoff is the human- and agent-readable thread that sits alongside it. Persist state.json as normal — a handoff never substitutes for it.

Scope

Keep the document to the live thread. When it starts restating the map or the spec, stop and link instead — a handoff that grows into a full project summary has become the artifact it was written to avoid.

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.