agentleFS
0xSoftBoi0xSoftBoi/suwappubot/.claude/skills/handoff/SKILL.md

handoff

Skill4 starsChanged 3 months agoApache-2.0View on GitHub

Dump the current task's state to .claude/handoff.md so the session can be /clear'd and resumed cheaply. Use at the end of a task, before switching topics, or any time the session has run long. Usage: /handoff [note]

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 47 projects that use this

  • RoentekSkill

    loop-me

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

    Also in 59 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 105 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 101 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 62 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is 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.

  • 1

    Very specific

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

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

    Write .claude/handoff.md (overwrite it) with only what a fresh session could not re-derive in one command.

    line 14
  2. Distinctive:

    Do not include: file contents, command output, the repo layout, anything already in CLAUDE.md, or narration of what happened.

    line 36
  3. Distinctive:

    If the task is genuinely finished and merged, write "State: done, nothing pending" and say so.

    line 50

“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 — checkpoint, then clear

Long sessions are the single largest source of token spend: every turn re-sends the entire conversation. A 1,000-turn session pays for its own history 1,000 times. This skill makes clearing cheap by writing down the only part worth keeping.

Do this

  1. Write .claude/handoff.md (overwrite it) with only what a fresh session could not re-derive in one command. Keep it under 40 lines.

    # Handoff — <YYYY-MM-DD> — <task in one line>
    
    ## State
    <done / in-progress / blocked, one line>
    
    ## Files touched
    - path:line — what changed and why
    
    ## Decisions made (and why)
    - <the reasoning a fresh session would otherwise redo>
    
    ## Next step
    1. <the single next concrete action>
    
    ## Dead ends — do NOT retry
    - <approach tried, why it failed>
  2. Do not include: file contents, command output, the repo layout, anything already in CLAUDE.md, or narration of what happened. A fresh session gets CLAUDE.md and git diff for free — don't pay to restate them.
  3. Reply with the path and a 3-bullet summary, then tell the user to /clear.

Resuming

A new session starts with: Read .claude/handoff.md, then git status && git diff --stat. That is the whole warm-up. If the handoff needed more than that, it was written wrong.

Rules

  • .claude/handoff.md is a scratch file, one task at a time — overwrite, never append.
  • If the task is genuinely finished and merged, write "State: done, nothing pending" and say so; don't manufacture next steps.

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.