hub
Skill4 starsChanged 56 days agoMITView on GitHub
Search and read what every other agent on this account has written. Use when you need context you did not produce yourself: what another agent is working on, whether something has been tried or decided before, or the text of a report somebody else wrote. Also use before starting work that might duplicate somebody else's.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- chanukawijeratna-ai/claude-session-hubtheir own version, first seen Nov 8, 2026
- RafalKielbasa/claude-skillstheir own version, first seen Nov 1, 2026
- Cleveland-RD/hivehousetheir own version, first seen Oct 13, 2026
- ilya-kozyrev/delamaintheir own version, first seen Oct 8, 2026
- ilya-kozyrev/claude-agent-hubtheir own version, first seen Oct 7, 2026
- ilanbm/kpoppertheir own version, first seen Sep 23, 2026
Used with
Projects with it also use handoff.
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.
MicrosoftSkillhandoff
Compact the current conversation into a handoff document for another agent to pick up.
Also in 3 projects that use this
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- Cleveland-RD/hivehouse★ 46same name
- ilanbm/kpopper★ 12same name
- ilya-kozyrev/claude-agent-hub★ 5same name
- ilya-kozyrev/delamain★ 5same name
- chanukawijeratna-ai/claude-session-hub★ 1same name
- RafalKielbasa/claude-skills★ 1same 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 repository5 other files it gives its agents.
- tb-voice/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- tb-voice/CLAUDE.mdCLAUDE.md
- research-hqSkill
- share-as-pageSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 5 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
5
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Every agent on this Mac mirrors its pages and its finished turns to a shared hub.
- Distinctive: line 50
Before research: somebody may have already done it, and the record will name what they concluded and what they rejected.
- Distinctive: line 52
When a page references work you cannot see: search its words rather than guessing.
- Distinctive: line 54
When the user asks what is happening, what is left, or who is on something.
- Distinctive: line 58
Not the web, and not this repository.
“Common” is measured: kept by at least 6 in 10 of the 5 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 hub
Every agent on this Mac mirrors its pages and its finished turns to a shared hub. That archive is readable from here. It is the answer to "has anyone looked at this already", and it is usually cheaper than redoing the work.
hq is on PATH. It carries this Mac's own key, so it only ever answers about
this account.
What is everyone working on
hq ask # the last 7 days, 10 agents
hq ask 1d 5 # narrowerReturns each agent with the last thing it said, how many turns and pages it has, and a url. Use this before starting something that sounds like somebody else's job.
Has this been looked at before
hq find "pairing phrase"
hq find "connection pool" 5Ranked across both turns and pages. Each hit is a POINTER: what it is, who wrote it, when, one fragment, and an address. It never returns a whole page, which is what keeps the answer small.
Then read the one that matters
hq turns <session-id> # that agent's own words, newest first
hq page <session-id> <slug> # one page, as textBoth take the session id printed in a search result. hq turns takes
detail=full shaped arguments through the API if you need what it found and
why, but the short form is usually enough.
When to reach for this
- Before research: somebody may have already done it, and the record will name what they concluded and what they rejected.
- When a page references work you cannot see: search its words rather than guessing.
- When the user asks what is happening, what is left, or who is on something.
What it is not
Not the web, and not this repository. It is what the agents on this account have written: their reports, and the structured turn each one files when it finishes. If the answer is not there, say so rather than inventing it.
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.