desktop [ library ]community courses orbits

dispatch / 2026-07-06_

[x] discovered
[x] decided
[ ] built
[ ] shipped_

     you
      |
   [ baton ]
   /   |   \
  v    v    v
 m1   m2   m3
  \    |    /
   \   |   /
    build_

 ┌─ context pack ─┐
 │ hash           │
 │ claims         │
 │ sources        │
 │ must-not       │
 └───────┬────────┘
         | open
         v
      new agent_

 ~\(@_@)/~
  /|   |\
 ~ |~~~| ~
  (_| |_)

  _
 ( o)
 |  \________
 |           \__
 |   ____       |
  \_|    |______|
   |__|  |__|  o

   _  _  _
 _| V| V| |_
/      o      \
|           __|
|    |  |  |
 |___|__|__|

   /\
  /  \
 | == |
 | || |
/|_||_|\
  /||\
 ' '' '

~~~~~~~~~~~~
 ~  ~  ~  ~

 /------\
 | nb:  |
 | yes_ |
 \------/


   /
  /
\/

┌──────────┐
│ decide   │
│ later    │
│    ···   │
└──────────┘

  .---.
 / hmm \
 \  ?  /
  '---'
   o
  o

    .
   /
  /---->
 /
*

 .--. .--.
(    Y    )
 \       /
  \     /
   \   /
    \_/

>_
 █

++*o++###+**###o#+++###+*o+#oo*#####*o#*+#*###*##+##*#o##o#+###+

#
o
#
#
*
#
o
#
*
o
#
#
*
o
#
*
+
#
o
#

[ notebook ]2026-07-06

Stop handing context to your agents. Pack it.

ready plan

classify

SMLXL

S / M · direct

one worker

L / XL · orchestrate

fable

fan out · reassemble

every worker reads its Context Pack

A plan comes in. It leaves as finished work, each piece routed to the cheapest model that can do it.

Hand a cheap model a task and it re-reads everything, or confabulates the one ID that actually mattered.

So I pack it instead. A Context Pack is one file: exact needles (ids, paths, values) kept verbatim, the bulk gisted, sized to half the model's window. Workers read what matters and re-fetch the rest.

context-pack.md

Decode headerhow to read this

Taskspec + done

Needleskept exact

7f3a9c2e1b8d/etc/app/config.yamlNEVER push to remote

Gist bulkrecognition only

File indexre-fetch exact bytes

/lib/context_pack.mjs/workflows/swarm.mjs

One file. The needles stay exact. Everything else is gist you can re-fetch.

needle extractor

paste text

what the pack keeps

Deploy commit 7f3a9c2e1b8d to the box.

Config lives at /etc/app/config.yaml, port 8080.

NEVER push to the remote before the gate passes.

The rest is background: we tried a few approaches

last week and settled on the simple one, which reads

fine and does not need to be exact to be useful.

4 needles kept verbatim. The rest greys to gist you re-fetch.

Type anything. The exact needles stay sharp, the bulk fades to gist.

A manager routes each task to the cheapest Claude tier that can do it, on your subscription, never metered. Small jobs go direct. Big ones fan out under a cheap large-context model that reassembles the result.

router

Shaikulow

Msonnetmedium

Lfablehigh

XLfablehigh · fan-out

on retry, escalatehaikusonnetopus

Complexity picks the model. No point burning the big one when the small one does the job.

I shipped this repo by pointing the tool at itself. It said "12 ok". I believed it only after diffing every file, because a workflow once told me "ok" for work it never ran.

Verify the behaviour, not the tally.

The whole thing is MIT and built with Claude: github.com/PUSHINGSQUARES/Build.

↓The /swarm skill (Build), ready to drop into your Claude Code

[ comments ]

guests welcome. members show first in the list

no comments yet. start the thread_

#
o
#
#
*
#
o
#
*
o
#
#
*
o
#
*
+
#
o
#

+*#*o#o##+##o#o##**oo*##*#***##+###oo*#**o#*o#+##o+#**o##+#++#o+