dtiger1889-opsdtiger1889-ops/claude-harness-toolbox/skills/spinoff/SKILL.md

spinoff

Skill31 starsChanged 32 days agoMITView on GitHub

Starts a separate session for a side topic from a short brief rather than copying the whole conversation. Use only for /spinoff, "spin this off", "hand this off to a new session", or "take this to its own session". Does not trigger automatically or replace a conversation fork.

3 other projects use a version of this.

Adopted by

Most recently taken up by

pche-broken-artist/forge-of-thoughttheir own version, first seen Nov 6, 2026
AhmedMerza/agent-skillstheir own version, first seen Oct 11, 2026
AhmedMerza/claude-skillstheir own version, first seen Sep 22, 2026

Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
pche-broken-artist/forge-of-thought★ 12same name
AhmedMerza/agent-skills★ 2same name
AhmedMerza/claude-skills★ 2same name
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 repository16 other files it gives its agents.
- breakdownSkill
- checkpointSkill
- decisionsSkill
- dumbSkill
- fanoutSkill
- grill-meSkill
- logSkill
- necromancySkill
- new-projectSkill
- outsideSkill
- plainSkill
- preventSkill
- proveSkill
- redteamSkill
- specSkill
- vetSkill

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 3 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

Very specific:
Write a short brief in a scratch location as spinoff-<UTC timestamp>-<slug>.md:
line 10
Distinctive:
Use the host's documented session-creation tool or configured launcher.
line 23
Distinctive:
Check the installed CLI's support before use.
line 29
Distinctive:
If launch fails, give the brief path and failure reason.
line 31
Distinctive:
Only include a report-back instruction when the user has authorized messaging the destination and any return message.
line 33
Distinctive:
If the user brings the topic back here, respect that direction.
line 35

“Common” is measured: kept by at least 6 in 10 of the 3 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

Spin off a side topic

Identify the side topic from the request or current detour. Ask once only if multiple topics fit.
Choose the existing project whose scope owns it; use the current project if no clearer owner exists. State the destination.

Write a short brief in a scratch location as spinoff-<UTC timestamp>-<slug>.md:

Topic: <side topic>
Request: <what the user asked>
Read first: <project instructions and current state>
Known: <evidence, relevant paths, commands, and errors>
Decided: <settled choices and their authors, or none>
First action / question: <the actual user request's next step; it never drops a source or deliverable the Request line names, so a two-source ask keeps both here>
Boundaries: <scope and pending approvals>

Include only the side topic and what the new session needs to work independently. Do not replace an action request with an abstract question. Keep the brief concise without omitting necessary evidence.

Use the host's documented session-creation tool or configured launcher. On Claude Code with background sessions supported, run from the chosen project:
```
claude --bg --name "<project>: <topic>" (Get-Content -Raw "<brief path>")
```
Check the installed CLI's support before use. Do not change workspace trust, permission mode, or active sessions to make it launch.
Confirm the actual session name and ID returned by the launcher, then return to the main task. For Claude Code, the user can attach with claude attach <id>.
If launch fails, give the brief path and failure reason. Do not claim a session started or run a retry ladder.

Only include a report-back instruction when the user has authorized messaging the destination and any return message. A new-session request does not authorize sending to unrelated sessions. If messaging is unsupported, leave the brief as the handoff artifact.

If the user brings the topic back here, respect that direction; do not force them into the other session.

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