agentleFS
clideyclidey/whodb/.agents/skills/task-handoff/SKILL.md

task-handoff

Skill5.1k starsChanged 3 days agoApache-2.0View on GitHub

Prepare or consume a concise handoff for multi-session or multi-agent work

7 other projects use a version of this.

Trending

Less talk lately.about the whole repository

Dec 2025: 0 mentionsJan 2026: 0 mentionsFeb 2026: 3 mentionsMar 2026: 8 mentionsApr 2026: 4 mentionsMay 2026: 5 mentionsJun 2026: 6 mentionsJul 2026: 5 mentionsAug 2026: 6 mentionsSep 2026: 6 mentionsOct 2026: 9 mentionsNov 2026: 0 mentions
Dec 2025Jun 2026Nov 2026
Mentions a month of the clidey/whodb repository that our weekly crawl found. There is no adoption data for this file yet.

Most recently taken up by

Who's talking about clidey/whodb

The biggest 5 of 60 mentions linking to the repository that our crawl found. Each line is their own headline.

See all 60

Talked about on GitHub, Bluesky and Hacker News (60 times).

On GitHub · 50

45 more on GitHub

On Bluesky · 7

2 more on Bluesky

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this workflow when work will continue in another session, another worktree, or another agent.

    line 8
  2. Distinctive:

    Keep the next step actionable.

    line 50
  3. Distinctive:

    If the handoff is for a parallel agent, include explicit file ownership to avoid conflicts.

    line 51
  4. Distinctive:

    Read the handoff before inspecting unrelated files.

    line 55
  5. Distinctive:

    Verify whether the stated next step is still valid.

    line 58

“Common” is measured: kept by at least 6 in 10 of the 5 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

Task Handoff

Use this workflow when work will continue in another session, another worktree, or another agent. Keep the handoff short enough to read before coding.

When to Create a Handoff

  • The task is not complete and another session needs to continue it.
  • A second agent or worktree needs enough context to avoid duplicating or reverting work.
  • The implementation has unresolved risks, skipped verification, or important decisions that are not obvious from the diff.
  • The user asks to pause, continue later, or hand work to another tool.

Handoff Format

## Goal
One sentence describing the intended end state.

## Current State
- What changed so far.
- What still needs to happen.
- Any user constraints that must be preserved.

## Files Touched
- `path/to/file`: why it changed.

## Decisions
- Decision made and why.

## Verification
- Command run: pass/fail and relevant result.
- Command not run: reason.

## Risks
- Known risk, blocker, or follow-up.

## Next Step
The first concrete action the next agent should take.

Rules

  • Be factual. Do not include speculation unless it is clearly marked as a risk or assumption.
  • Mention unrelated dirty worktree changes separately so the next agent does not revert user work.
  • Include exact commands, paths, and error text when they matter.
  • Keep the next step actionable. Avoid vague instructions like "continue implementation."
  • If the handoff is for a parallel agent, include explicit file ownership to avoid conflicts.

Consuming a Handoff

  1. Read the handoff before inspecting unrelated files.
  2. Check git status --short --untracked-files=all.
  3. Re-read the files listed under Files Touched.
  4. Verify whether the stated next step is still valid.
  5. Continue with the smallest change that moves the handoff goal forward.

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.