agentleFS
CowboyLogicCowboyLogic/ai-dev/skills/handoff/SKILL.md

handoff

Skill4 starsChanged 11 days agoMITView on GitHub

Write a curated, size-capped handoff file that carries task state from this session to a fresh one. Run only when the user invokes /handoff.

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

9 rules. 0 are common, 6 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 172 edited versions we read keep these.

  • 6

    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:

    Write one live file, .agent-output/handoff.md, so a fresh session can pick up this task where it stopped.

    line 10
  2. Distinctive:

    Run this before the first write, from inside the repository:

    line 17
  3. Distinctive:

    Exit 1 (not ignored): stop and ask which the user prefers.

    line 24
  4. Very specific:

    A. Create .agent-output/ and add .agent-output/ to the repository's .gitignore.

    line 26
  5. Very specific:

    Create .agent-output/ if it does not exist, then write the file in this shape.

    line 42
  6. Distinctive:

    Keep the whole file to about 100 lines.

    line 69
  7. Distinctive:

    Leave out anything a fresh session can derive from git log, git diff, or the code.

    line 70
  8. Distinctive:

    Leave out durable facts and preferences.

    line 71
  9. Distinctive:

    Never include credentials, tokens, or secrets.

    line 72

“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

Write one live file, .agent-output/handoff.md, so a fresh session can pick up this task where it stopped. Overwrite any previous handoff. The file holds task state only, not durable facts: those belong in the harness's memory feature.

1. Check that the path is ignored

A handoff can hold proprietary context, so never write it to a path git would stage. Run this before the first write, from inside the repository:

git check-ignore -q .agent-output/handoff.md
  • Exit 0 (ignored): continue to step 2.
  • Exit 1 (not ignored): stop and ask which the user prefers. Write nothing until they answer.
    • A. Create .agent-output/ and add .agent-output/ to the repository's .gitignore. This is a tracked change that every contributor receives.
    • B. Append .agent-output/ to the file printed by git rev-parse --git-path info/exclude. This is untracked and applies to this clone only.
  • Not a git repository (the command reports that): continue to step 2. There is nothing to ignore.

2. Gather the header facts

  • Timestamp: date -u +%Y-%m-%dT%H:%M:%SZ
  • Branch: git symbolic-ref --short -q HEAD. If that prints nothing, use (detached). Outside a git repository, use (none).

3. Write the file

Create .agent-output/ if it does not exist, then write the file in this shape. The header lines must keep this exact form, because the session-start hook reads the Branch: line.

# Handoff

Written: <timestamp>
Branch: <branch>

## Goal and current state
## Decisions
## Gotchas and dead ends
## Next step
## In-flight work
## Open questions
  • Goal and current state: what the task is and how far it got.
  • Decisions: each decision with the reason for it.
  • Gotchas and dead ends: approaches already tried and why they failed.
  • Next step: the exact next action, specific enough to start without re-deriving it.
  • In-flight work: uncommitted or half-done changes, by file.
  • Open questions: what still needs an answer, and from whom.

Rules:

  • Keep the whole file to about 100 lines. Cut to fit.
  • Leave out anything a fresh session can derive from git log, git diff, or the code.
  • Leave out durable facts and preferences. They belong in memory, not here.
  • Never include credentials, tokens, or secrets.
  • Omit a section only if it is truly empty. Write None rather than inventing content.

4. Report back

Tell the user the path, the line count, and that the file is meant to be reviewed before use. Suggest /clear when they are ready to continue in a fresh session. Do not run it for them.

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.