handover
Skill1 starsChanged 17 days agoApache-2.0View on GitHub
Hand this session's Coordinator role or claimed Lead node to another session. Drafts the handover note in its four sections from the current work and calls `role.handover` through the cland spoke. Use when the human asks you to hand over, or when you must stop leading your node.
53 other projects use a version of this.
Adopted by
Most recently taken up by
- gjoranv/claude-plan-skillstheir own version, first seen Nov 15, 2026
- yagizdo/quivertheir own version, first seen Nov 15, 2026
- thiagobluhm/o1memtheir own version, first seen Nov 8, 2026
- randommonicle/claude-skillstheir own version, first seen Nov 5, 2026
- hmislk/hmistheir own version, first seen Nov 2, 2026
- loonylabs-dev/claude-setuptheir own version, first seen Nov 1, 2026
Used with
Projects with it also use harness-init, incident and 4 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.
steptianSkillharness-init
初始化 .harness 开发框架,集成代码修改影响范围评估和测试覆盖建议功能。触发词:'初始化新项目'、'harness init'、'更新 harness'、'分析影响范围'、'评估修改影响'
Also in 3 projects that use this
JkudjoSkillincident
Production incident response — structured triage, hypothesis tree, safe remediation, incident record
Also in 3 projects that use this
nicolasestremSkillbrainstorm
Structured idea generation and solution exploration with systematic analysis.
Also in 4 projects that use this
BlockSkillplan
Draft a TDD, PRD, or lightweight plan in the conversation without committing it.
Also in 4 projects that use this
Microsoft AzureSkilldesign
Design rules and conventions for the API Center Portal. Use when editing detail pages, card components, badges, layout, navigation, sidebars, or headers. Covers badge styling, metadata placement, page navigation patterns, and layout alignment.
Also in 3 projects that use this
MicrosoftSkillcaveman
Ultra-compressed response style that reduces output token count while preserving technical accuracy, with intensity levels and auto-clarity safety rules
Also in 3 projects that use this
Other versions53 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 53
- me2resh/apexyard★ 542same name
- hmislk/hmis★ 245same name
- chenklein26-maker/Harness-Starter★ 119same name
- k1ein-chen/Harness-Starter★ 119same name
- eai-org/agent-toolkit★ 94same name
- manusco/resonance★ 38same name
- chacosoldier/compabob★ 34same name
- randommonicle/claude-skills★ 27same name
- yagizdo/quiver★ 16same name
- L-X-T/ng-agentic-skills★ 13same name
43 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.
- AGENTS.mdAGENTS.md
- codebase-designSkill
- code-reviewSkill
- diagnosing-bugsSkill
- domain-modelingSkill
- grillingSkill
- implementSkill
- mergeSkill
- onboardingSkill
- plan-epicSkill
- prototypeSkill
- qaSkill
- releaseSkill
- researchSkill
- retroSkill
- tddSkill
- to-specSkill
- to-ticketsSkill
- triageSkill
- wayfinderSkill
- writing-for-agentsSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 1 is distinctive, and 4 are very specific to this project.
0
Common
Most of the 40 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 29
Write four sections in this order, none of them empty.
- Very specific: line 45
If a section truly has nothing in it, say so in one line (Nothing waiting.).
- Distinctive: line 47
If the human asked for the handover, show them the draft and apply their changes.
- Very specific: line 51
Call the spoke tool role.handover with to and note.
- Very specific: line 53
If the result has code: "invalid_argument", correct the named fields and retry (for example, supply the required note).
“Common” is measured: kept by at least 6 in 10 of the 40 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
The next holder continues from the note and the hub. It never sees your transcript (spec 4.4, ADR 0001). Write the note so that a session which has seen none of this conversation can pick up the work.
1. Find the receiver
The argument names the session that takes the role. Call who. The receiver must be connected, or be a session launched through the hub (cland session list --json). The separate session.list read grant is held by every role by default; it grants no session lifecycle mutations.
- A Coordinator asks the human when no receiver is named. If the human wants a fresh receiver, launch it with
session.launchand give it no role; the role arrives with the handover. - A Lead's receiver must hold no item claim. If a receiver must be chosen or launched, send a question to
lead T-<n>for your claimed node, naming the missing receiver; the question climbs to the supervising Lead or Coordinator.
Leads hand over their own claimed node; other Leads keep theirs.
2. Gather what the note rests on
Take the facts from the hub and the tracker, not from memory alone:
role.state: the topics waiting for the role, the open asks and the claims you hold. For a Lead, confirm itsitemand single node claim; state belongs to that node.task.listfor the open items and the ones assigned to or claimed by you, andtask.viewfor the ones in flight.history, plushistorywith atopicfor each topic that is waiting.
3. Draft the note
Write four sections in this order, none of them empty. Keep the lines short. Name items by id (T-12), sessions by name and topics by id. Point at items, files and topics instead of copying them.
## Goals now
What your project or claimed node is driving at right now: the one to three outcomes the next holder steers toward.
## Work in flight
Each piece of work in your node that is moving: the item, who does it, where it stands, what comes next.
## Open decisions
What is still undecided, the options on the table, and who decides (the human through `ask`, or the Coordinator).
## Waiting on
What is blocked on someone else: the human, a Reviewer or QA verdict, a session's reply. Name who, and since when.If a section truly has nothing in it, say so in one line (Nothing waiting.). The hub refuses an empty section.
If the human asked for the handover, show them the draft and apply their changes.
4. Hand over
Call the spoke tool role.handover with to and note. The note is the Markdown above, or an object with goals_now, work_in_flight, open_decisions and waiting_on. Pass then: "implementer" only when the human wants you to stay on as an Implementer.
- If the result has
code: "invalid_argument", correct the named fields and retry (for example, supply the requirednote). A supplied Markdown note or empty section may return{ ok: false, code: "note-incomplete", missing }; fill in those sections and retry. - For any other refusal, tell the human what it says. Do not retry it another way.
5. Stop
When the handover succeeds, the hub sends you a "role revoked" event (with then, your Implementer clause instead). From that moment you no longer act in the handed-over role: no messages on its behalf, no item edits, no launches. The Coordinator's claims, or the Lead's node claim and default subscriptions, have moved to the new holder. Continue only in the role named by the new clause or on a new assignment.
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.

