agentleFS
Sign inStart free
tanishq286tanishq286/tq-forge/skills/handoff/SKILL.md

handoff

Skill8 starsChanged 5 months agoMITView on GitHub

Write a HANDOFF.md that lets a fresh chat continue this work with a small context. Use when asked for "/handoff", when the session is long or slow, or when the handoff mod reports that the chat passed 250,000 tokens.

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

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

  • 1

    Very specific

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

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

    Read .claude/HANDOFF.md. Check the Goal and the file lists against what actually happened, and fix anything wrong.

    line 25
  2. Distinctive:

    Add anything a new chat could not rediscover from the files: a failing command and its error, a constraint the user gave, a path that looks …

    line 27
  3. Distinctive:

    Write what is true now, not what was planned.

    line 32
  4. Distinctive:

    Do not paste file contents into the handoff.

    line 33

“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

When to use

Run this when a session has grown large enough that every turn is expensive, or when the user wants to stop and pick the work up later. The mod builds the factual part from the transcript (what was asked, which files were read and changed, which skills and URLs were used); you add the part only you know, which is the state of the work.

Procedure

  1. Build the skeleton from the transcript:
M="$HOME/.claude/hooks/tq-forge/mods.py"; [ -f "$M" ] || M=".claude/hooks/tq-forge/mods.py"
python3 "$M" handoff --cwd "$PWD"
  1. Read .claude/HANDOFF.md. Check the Goal and the file lists against what actually happened, and fix anything wrong.
  2. Replace the placeholder under "State of the work" with: what is finished and verified, what is not finished, each decision and the reason for it, and the next three steps in order.
  3. Add anything a new chat could not rediscover from the files: a failing command and its error, a constraint the user gave, a path that looks wrong but is right.
  4. Tell the user the file is ready and that they can start a new chat with: "Read .claude/HANDOFF.md and continue."

Pitfalls

  • Write what is true now, not what was planned. A step that was not verified is not finished.
  • Do not paste file contents into the handoff. Point to the file and the line.
  • The skeleton lists every file that was read. Remove the ones that turned out not to matter.

Verification

  • .claude/HANDOFF.md has no placeholder text left.
  • Someone who reads only that file could name the next step.

Tags

handoff, context, session, mods

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