vinzenz/hyperhive
vinzenz/hyperhive
Watch
0
0
Fork
You've already forked hyperhive
 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1

treefmt: apply prettier

Browse source 
Pure `nix fmt` output from the commit before this one — no hand edits.
203 files: 52 md, 42 tsx, 32 js, 32 css, 21 ts, 13 html, 8 json, 3 mjs.

Reproduce with `nix develop -c nix fmt` on the parent commit; the result
should be byte-identical to this tree.

None of the 13 `.prettierignore` entries appears here — verified by
intersecting the changed-file list against the ignore file, with a
control proving the intersection finds a match when one exists.
This commit is contained in:
atlas 2026-09-02 14:29:33 +02:00
commit 39b95c2ede
203 changed files with 10090 additions and 6085 deletions
Download patch file Download diff file Expand all files Collapse all files

6
claude-plugins/plugins/base/skills/claude-subagents/SKILL.md
View file

@ -33,7 +33,7 @@ claude --name <memorable> --model <cheaper-than-you> --dangerously-skip-permissi
by name for follow-ups.
- **`--model <cheaper-than-you>`** - think about which model the task
actually needs; don't spend a bigger model's tokens than your own on
mechanical work a cheaper one handles fine. Never use a *bigger* model
mechanical work a cheaper one handles fine. Never use a _bigger_ model
than yourself for a sub-agent - if the task needs that much capability,
it's not the "mechanical batch" case this skill is for.
- **`--dangerously-skip-permissions`** - required in headless (`-p`)
@ -68,7 +68,7 @@ work while the sub-agent grinds.
cases: "leave it as-is where genuinely unclear; do not guess."
- **Ask for a report file** - per-item results + anything skipped and
why, so you can verify without re-deriving.
- **Tune on ONE item first**, eyeball the result, fix the prompt, *then*
- **Tune on ONE item first**, eyeball the result, fix the prompt, _then_
turn it loose on the full batch. A prompt bug replicated across 100
items is 100 cleanups.
@ -98,7 +98,7 @@ running at once instead of handing the whole thing to one.
loop.
- **Mind the container's memory cap before picking N.** Your whole
container shares one `MemoryMax` (a few GB by default) with every
subagent you spawn *and* your own process. A `claude` process plus its
subagent you spawn _and_ your own process. A `claude` process plus its
MCP servers can hold several hundred MB to ~1GB depending on the task;
spawning a dozen at once on a small container doesn't just slow
things down, it can OOM the whole container — taking your own