handoff
Skill8 starsChanged 5 months agoMITView on GitHub
Write a handoff document so another agent or a fresh session can continue this work. Use for "handoff", "hand this off", "write a handoff", "continue this in a new session" or "pass this to another agent". For deciding whether to compact or clear, use session-budget.
191 other projects use a version of this, 87 of them edited.
Adopted by
Most recently taken up by
- tanishq286/tq-forgetheir own version, first seen Nov 15, 2026
- niki914/zafiroedited, first seen Nov 15, 2026
- davidondrej/skillstheir own version, first seen Nov 15, 2026
- quickchatai/quickreviewedited, first seen Nov 15, 2026
- HiteSit/real-scientist-skillsedited, first seen Nov 15, 2026
- alexj11324/Mikkaedited, 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 · 87
- mattpocock/skills★ 325k34% same
- QuivrHQ/quivr★ 40k36% same
- The-Vibe-Company/quivr★ 40k36% same
- GreyDGL/PentestGPT★ 16k40% same
- ArcReel/ArcReel★ 6.6k34% same
- withcoral/coral★ 4.9k34% same
- bestofjs/bestofjs★ 3.1k37% same
- compozy/compozy★ 2.9k36% same
- bholmesdev/hubble.md★ 1.5k41% same
- CelestoAI/SmolVM★ 1.2k39% same
77 more not listed
Wrote their own version · 104
- ykdojo/claude-code-tips★ 10ksame name
- vinvcn/mattpocock-skills-zh-CN★ 5.8ksame name
- epicenter-md/epicenter★ 4.8ksame name
- EpicenterHQ/epicenter★ 4.8ksame name
- davidondrej/skills★ 4.3ksame name
- feiskyer/claude-code-settings★ 1.7ksame name
- skforecast/skforecast★ 1.5ksame name
- openclaw/agent-skills★ 1.1ksame name
- suboss87/FDEOps★ 940same name
- JordanCoin/codemap★ 715same name
94 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 repository32 other files it gives its agents.
- AGENTS.mdAGENTS.md
- agents-md-lintSkill
- auto-scopeSkill
- cavemanSkill
- completeSkill
- councilSkill
- deskSkill
- discernmentSkill
- doSkill
- dreamSkill
- humanizeSkill
- laymanSkill
- offloadSkill
- prototypeSkill
- pr-reviewSkill
- red-penSkill
- review-securitySkill
- session-budgetSkill
- writing-commitsSkill
- writing-plan-documentsSkill
- writing-sqlSkill
- design-consultationSkill
- design-reviewSkill
- investigateSkill
- plan-deep-reviewSkill
- plan-design-reviewSkill
- plan-devex-reviewSkill
- plan-eng-reviewSkill
- plan-sessionSkill
- qa-onlySkill
- qaSkill
- reviewSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 5 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 172 edited versions we read keep these.
5
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
- Distinctive: line 7
Write a handoff document summarising the current conversation so a fresh agent can continue the work.
- Distinctive: line 9
If the user passed arguments, treat them as a description of what the next session will focus on and tailor the doc accordingly.
- Distinctive: line 12
When continuing a complete run, include its ledger and per-slice result paths under Pointers, and preserve authorization, frozen gates, …
- Distinctive: line 32
Don't duplicate content already captured in other artifacts (PRDs, plans, ADRs, issues, commits, diffs).
- Very specific: line 33
If a section has no real content, write None.
- Distinctive: line 34
Keep it tight. A handoff is a launchpad, not a transcript.
“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
Write a handoff document summarising the current conversation so a fresh agent can continue the work. Create a unique temporary directory with the platform's secure temp helper (for Node, fs.mkdtempSync(path.join(os.tmpdir(), "handoff-"))) and write handoff.md inside it. Report the absolute path.
If the user passed arguments, treat them as a description of what the next session will focus on and tailor the doc accordingly.
Preserve the actual receiving runtime and resolved role/model configuration under Key context. Do not inject orchestration defaults into an unrelated continuation. Writing a handoff does not launch a worker or change the active model. When continuing a complete run, include its ledger and per-slice result paths under Pointers, and preserve authorization, frozen gates, unresolved rulings, and agent IDs needed to resume. The receiving Codex must verify agent liveness; an ID from a previous session is not proof that a worker is still running.
Document structure
The handoff is read by another agent, so its shape is fixed. Produce exactly these eight sections, in this order, with these headings verbatim. Lead with intent and next steps, not narrative history — a fresh agent should scan top to bottom and start working.
# Handoff: <short title>— one line naming the work.## Goal— what the next session is trying to accomplish, in 1–2 sentences. If args were passed, this reflects them.## Current state— what's done and working right now. Bullets, past tense.## Next steps— the concrete actions to take next, ordered, each an imperative ("Wire up X", "Run Y"). The most important section: make it actionable from a cold start.## Open questions / blockers— unresolved decisions, things waiting on someone, known risks.## Key context— the non-obvious things: decisions made and why, gotchas, dead ends already ruled out. Skip anything a fresh agent could read straight from the code or the linked artifacts.## Pointers— paths and URLs to the artifacts that hold the detail: PRDs, plans, ADRs, issues, branches, key files (path:line). Reference them; don't copy their contents in.## Suggested skills— which skills the next session should use, if any, and for what.
Rules
- Don't duplicate content already captured in other artifacts (PRDs, plans, ADRs, issues, commits, diffs). Reference them by path or URL instead — that's what Pointers is for.
- If a section has no real content, write
None.under it rather than padding with filler or inventing items to fill space. An empty Open questions is fine; a fabricated one is not. - Keep it tight. A handoff is a launchpad, not a transcript.
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.

