agentleFS
Sign inStart free
ethosagentethosagent/ethos/.agents/skills/handoff/SKILL.md

handoff

Skill22 starsChanged 11 days agoMITView on GitHub

Write HANDOFF.md at the repo root: what is done, what remains, the failing gate with its .logs/ path, open decisions, and files touched. Use before ending a session or when asked to hand off.

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:

    Write HANDOFF.md at the repo root so a fresh session can resume without this conversation.

    line 8
  2. Distinctive:

    Run these first, read-only:

    line 12
  3. Distinctive:

    Keep it short: a reader should finish in a minute.

    line 32
  4. Very specific:

    Do not commit HANDOFF.md.

    line 33
  5. Very specific:

    After writing, confirm with grep -c '^## ' HANDOFF.md, which must print 5.

    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

Handoff

Write HANDOFF.md at the repo root so a fresh session can resume without this conversation. The file is gitignored (/HANDOFF.md) and local only.

Gather

Run these first, read-only:

  1. git status --short
  2. git diff --stat main...HEAD
  3. The newest .logs/*.log with a non-zero result: list with ls -t .logs/*.log, open the newest ones until a failure shows. If none failed, say so.
  4. The active plan path, by the same rule as session-compact.sh: plan/.active if it exists (its contents name the plan), else the newest-mtime file across plan/*.md and plan/phases/*.md.

Write

Overwrite HANDOFF.md, never append. Use exactly five H2 headings, in this order, and no others:

  • ## Done: what is finished and verified this session, one bullet each. Cite the commit or test that proves it.
  • ## Remaining: what is left, in order, naming the active plan path and the next task or step in it.
  • ## Failing gate: the gate that failed (typecheck, lint, test, archcheck), its .logs/ path, and the first error lines. Write None if everything passed.
  • ## Open decisions: questions that need the maintainer, each with the options and your recommendation.
  • ## Files touched: paths from git status and git diff --stat, each with a few words on what changed.

Rules

  • State only what you checked. Mark anything unverified as unverified.
  • Keep it short: a reader should finish in a minute.
  • Do not commit HANDOFF.md.
  • After writing, confirm with grep -c '^## ' HANDOFF.md, which must print 5.

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