handoff
Skill173 starsChanged 17 days agoMITView on GitHub
Checkpoint work for recovery — fires on "handoff", "wrap up", context pressure, a closed phase, or before a long external wait or irreversible gate. Part of the Agentsmith harness; writes durable state plus a paste-ready kickoff block so a fresh session loses nothing.
191 other projects use a version of this.
Adopted by
Most recently taken up by
- xiaoxiaosrm/dsh-mattpocock-skillstheir own version, first seen Nov 8, 2026
- ethosagent/ethostheir own version, first seen Nov 8, 2026
- dsifry/metaswarmtheir own version, first seen Nov 8, 2026
- glebis/claude-skillstheir own version, first seen Nov 8, 2026
- domengabrovsek/agent-configtheir own version, first seen Nov 8, 2026
- domengabrovsek/claudetheir own version, first seen Nov 8, 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★ 309ksame name
- QuivrHQ/quivr★ 40ksame name
- The-Vibe-Company/quivr★ 40ksame name
- GreyDGL/PentestGPT★ 16ksame name
- ykdojo/claude-code-tips★ 10ksame name
- ArcReel/ArcReel★ 6.3ksame name
- vinvcn/mattpocock-skills-zh-CN★ 5.5ksame name
- withcoral/coral★ 4.9ksame 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 repository11 other files it gives its agents.
- AGENTS.mdAGENTS.md
- autonomous-runSkill
- example-skillSkill
- grill-with-docsSkill
- harness-doctorSkill
- harness-helpSkill
- new-feedbackSkill
- new-researchSkill
- verifySkill
- wayfinderSkill
- writing-rulesSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 172 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 23
Run agentsmith handoff [item-id] — use .agentsmith/agentsmith on macOS/Linux or .agentsmith\\agentsmith.cmd on Windows when the command is …
- Very specific: line 34
Write .harness/handoffs/handoff-<stamp>.md with these sections:
“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 — memory first, then the kickoff
A fresh session has zero memory of this one; the handoff note is the only bridge. Run this whenever work winds down — even if no one asked (core/50).
When this fires
"handoff" / "wrap up" / "let's stop here" / context pressure / a closed phase / before a long external wait, merge, release, deployment, or other irreversible external gate.
Runtime neutrality
This workflow is identical in every client. Never infer the active agent from this skill's install
path: portable canonical content may be copied into a required client adapter such as
.claude/skills. Use “fresh chat” rather than a runtime-specific reset command so the note remains
portable.
Fast path — if the Agentsmith CLI is available
- Run
agentsmith handoff [item-id]— use.agentsmith/agentsmithon macOS/Linux or.agentsmith\\agentsmith.cmdon Windows when the command is not on PATH. It pre-fills branch/HEAD/dirty count and scaffolds.harness/handoffs/handoff-<stamp>.mdwith the standard sections. - Fill the scaffolded sections (below). Before you treat the note as saved, run
agentsmith secret-scan <note path>; on a finding, replace the value with the name of the resource and scan again. Then emit the kickoff block as your final message.
Fallback — no CLI
- Safe state FIRST (core/50 step 1): commit or stash so nothing half-edited is lost. Never hand off a dirty tree silently.
- Write
.harness/handoffs/handoff-<stamp>.mdwith these sections:- Recovery checkpoint — exact objective; repository/worktree; protected-state hashes; branch/commit and external identifiers; completed/skipped verification; active operation; next read-only recovery command; remaining authorized writes; stop conditions.
- What shipped this session — with commit SHAs / PR links.
- Verified this session — the checks you ran in this session, with command and result.
- Carried over, not re-verified — claims from earlier notes or other agents you did not re-check. Never move a claim into "verified" without running its check.
- What is still pending.
- Open questions — default if unanswered — each question with the default the next session takes if nobody answers.
- Deviations / decisions made (so they're not re-litigated).
- Exact next step — the single first action for the next session.
- Gotchas a fresh session would otherwise re-derive.
- Scan the note before you treat it as saved:
agentsmith secret-scan <note path>(or.agentsmith/agentsmith secret-scan <note path>). A handoff note is read by every later session, so a secret in it spreads. - Emit a fenced "Kickoff prompt for a fresh chat" block: 3–6 sentences of self-contained prose (not bullets — they paste it straight in) covering the item id, branch + HEAD, what's done, the single next step, decisions already made, and the handoff note path.
Report
Name the handoff file, then end your message with the fenced kickoff block. If you notice mid-wrap that you haven't written the note yet, stop and write it before continuing.
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.

