handoff
Skill1 starsChanged 4 months agoMITView on GitHub
Write a capped between-session brief (goal, where we are, next steps, decisions, gotchas) to ~/.claude/handoffs/<repo>.md, or read it back at the start of a fresh session. User-invoked: `/handoff` writes, `/handoff resume` reads. A deliberate handoff, not a compaction.
191 other projects use a version of this.
Adopted by
Most recently taken up by
- lhotwll217/owner-operatortheir own version, first seen Nov 16, 2026
- tanishq286/tq-forgetheir own version, first seen Nov 15, 2026
- niki914/zafirotheir own version, first seen Nov 15, 2026
- davidondrej/skillstheir own version, first seen Nov 15, 2026
- quickchatai/quickreviewtheir own version, first seen Nov 15, 2026
- HiteSit/real-scientist-skillstheir own version, first seen Nov 15, 2026
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.
FabienDehopreSkilldecision-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
liufeng1976Skillsetup-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
AWSSkillto-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
GoogleSkillask-matt
Ask which skill or flow fits your situation. A router over the skills in this repo.
Also in 87 projects that use this
RoentekSkillloop-me
Grill me about specs for the workflows I want to build, within this workspace.
Also in 51 projects that use this
LesaniSkillwriting-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
Other versions191 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 191
- mattpocock/skills★ 325ksame name
- QuivrHQ/quivr★ 40ksame name
- The-Vibe-Company/quivr★ 40ksame name
- GreyDGL/PentestGPT★ 16ksame name
- ykdojo/claude-code-tips★ 10ksame name
- ArcReel/ArcReel★ 6.6ksame name
- vinvcn/mattpocock-skills-zh-CN★ 5.8ksame name
- withcoral/coral★ 5ksame name
- epicenter-md/epicenter★ 4.8ksame name
- EpicenterHQ/epicenter★ 4.8ksame name
181 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository21 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- ai-commentsSkill
- ai-draftSkill
- ai-nextSkill
- ai-postSkill
- call-traceSkill
- draft-prSkill
- dto-mappingSkill
- hum-commentsSkill
- jira-dcSkill
- meeting-summarySkill
- plan-from-issueSkill
- plan-nextSkill
- plan-reviewSkill
- plan-saveSkill
- pr-commentsSkill
- pr-statsSkill
- review-sessionSkill
- skill-builderSkill
- validator-generatorSkill
- templateSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 3 are distinctive, and 3 are 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.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 24
Write state, not history, and stay under the cap.
- Very specific: line 28
Locate: Run one command: git rev-parse --show-toplevel && git branch --show-current && git status --short.
- Very specific: line 42
Resume: Read the file. If it does not exist: handoff: none for <key> at <path>.
- Distinctive: line 51
Stop and wait for direction.
- Very specific: line 85
Empty section = one bullet
- none: Keep every heading so the reader knows nothing was dropped. - Distinctive: line 88
No preamble, no recap, no offers.
“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.
Files
Handoff: carry one piece of work from this session to the next
The next session starts with zero context and will trust this file. Write what a colleague needs to continue in ten minutes: the goal, what is done, what is next, what was decided and why, and what will bite them. The failure mode is the transcript dump: a long narrative of what happened. Write state, not history, and stay under the cap.
Steps
- Locate. Run one command:
git rev-parse --show-toplevel && git branch --show-current && git status --short. Repo key = basename of the toplevel; outside a repo, key =general, no branch, no status. Path =~/.claude/handoffs/<key>.md. - Branch on
$ARGUMENTS. Empty → step 3 (write).resume→ step 5 (read). Anything else → one line:handoff: unknown argument "<arg>" — use /handoff or /handoff resume. Stop. - Write the file at the path from step 1 in the Output format below, overwriting any previous
handoff for that key. Every bullet is a current fact, not a step you took.
Working treeis thegit status --shortoutput verbatim (omit the section when clean or outside a repo). Mark anything you did not verify this session(unverified). - Report and stop. Print
Handoff written: <path> (<N> lines). Nothing else. Resume. Read the file. If it does not exist:
handoff: none for <key> at <path>. Stop. If the handoff branch differs from the current branch, say so in one line. Then print exactly:Resumed <key> from <date> · <branch> Goal: <Goal line> Next: <first item under Next>Stop and wait for direction. Do not start the next step unasked.
Output format
# Handoff · <key> · <branch> · <YYYY-MM-DD HH:mm>
## Goal
<one sentence: the task and what "done" looks like>
## Where we are
- <done or in-progress fact, `path:line` where it helps>
## Next
1. <ordered step>
## Decisions
- <decision> — <why>
## Gotchas
- <trap, non-obvious behavior, command that fails and why>
## Working tree
<git status --short, verbatim>
## Refs
- <ticket key, PR URL, plan file, working-file path>Rules
- Cap: 60 lines total, max 6 bullets per section. Cut the least load-bearing item, never widen.
- State, not history. "Migration added, not yet applied" — not "then I added a migration".
- Verbatim identifiers. Ticket keys, paths, branch names, commands, error text exactly as seen.
- Empty section = one bullet
- none. Keep every heading so the reader knows nothing was dropped. - NEVER commit, push, or compact. The file is the deliverable.
- NEVER pad resume output. Three lines plus the optional branch warning; the file itself is the detail.
- No preamble, no recap, no offers.
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
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.

