agentleFS
flonatflonat/flonat-research/skills/handoff/SKILL.md

handoff

Skill150 starsChanged 10 days agoMITView on GitHub

Create, accept, or update the persistent `.context/ai-handoff.md` state shared by AI sessions and machines. Use when continuing in a new Claude or Codex session, transferring work between clients, or recording ownership and restart 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

10 rules. 0 are common, 3 are distinctive, and 7 are 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.

  • 7

    Very specific

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

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

    Use one client-neutral handshake for every route.

    line 8
  2. Very specific:

    If the user names Claude or Codex, use that client as to.

    line 12
  3. Very specific:

    If the user asks for the next or a fresh session without naming a client, set to to the current client.

    line 13
  4. Very specific:

    Use to: either only when the task is deliberately client-agnostic.

    line 14
  5. Very specific:

    All routes write <project-root>/.context/ai-handoff.md.

    line 17
  6. Very specific:

    Read only the relevant durable guidance and state: CLAUDE.md, AGENTS.md, the latest approved plan, current focus, recent log, and any …

    line 22
  7. Distinctive:

    Use the supplied outcome. If none is supplied, infer the highest-priority open loop.

    line 23
  8. Distinctive:

    Never overwrite project-owned CLAUDE.md or AGENTS.md: they remain durable client guidance.

    line 28
  9. Very specific:

    When .context/ai-handoff.md targets the current client or either:

    line 32
  10. Distinctive:

    Read both native guidance files and the handshake before editing.

    line 34

“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

Project Handoff

Use one client-neutral handshake for every route. Before acting, read ../shared/cross-client-handoff.md completely and follow its schema and state machine.

Choose the route

  • If the user names Claude or Codex, use that client as to.
  • If the user asks for the next or a fresh session without naming a client, set to to the current client. This is the default for Claude-to-Claude and Codex-to-Codex continuation.
  • Use to: either only when the task is deliberately client-agnostic.
  • Set from to the current client, or human when invoked outside a client session.

All routes write <project-root>/.context/ai-handoff.md. Do not create a separate client-specific handoff file.

Prepare a handoff

  1. Resolve the project root from the current working directory or the named project.
  2. Read only the relevant durable guidance and state: CLAUDE.md, AGENTS.md, the latest approved plan, current focus, recent log, and any existing handshake. Never inspect restricted data/raw/ content.
  3. Use the supplied outcome. If none is supplied, infer the highest-priority open loop; ask only if different choices would materially change scope.
  4. Reconcile the existing handshake. Preserve still-valid decisions and its log, then create a new handoff_id and set status: ready.
  5. Record the source and target client, source and target machine, branch, commit, exact working-tree ownership, observable acceptance criteria, real commands, and the first concrete action.
  6. Validate the YAML frontmatter and Markdown sections against the shared protocol. Check that the file contains no secrets, credentials, transcripts, caches, or restricted data.

Never overwrite project-owned CLAUDE.md or AGENTS.md: they remain durable client guidance. Never auto-commit or push the handshake.

Receive a handoff

When .context/ai-handoff.md targets the current client or either:

  1. Read both native guidance files and the handshake before editing.
  2. Compare the recorded branch, commit, machine, and changed-file ownership with the actual working tree.
  3. Set status: accepted and append a timestamped log entry before substantive work.
  4. Set status: in_progress when execution begins.
  5. Maintain acceptance criteria and the log. Finish with complete, or use blocked with the precise blocker and safe next action.

Transport and launch

  • Same machine: start the receiving client in the project root.
  • Dropbox project: let the project sync, then verify the recorded branch/commit and file ownership.
  • Git project on another machine: verify the remote, commit/push only with normal authorization, pull there, and run that distribution's documented client installer or sync command before starting the receiving client.

Report the handshake path, route, outcome, status, transport needed, and launch command. A completed handshake stays as a short audit trail until the next handoff reconciles it.

Compatibility

Root handoff.md is retired and ignored. Every new or resumed handoff must use .context/ai-handoff.md; it is the only format that supports same-client, cross-client, and cross-machine state tracking.

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.