Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yzhao062/prun
Parallel delegation fan-out. The Claude session coordinates (on whatever Claude model is currently selected, e.g. Opus or Fable) while task units run in parallel on workers (never on the coordinator). Codex (`codex exec`, a separate abundant account) is the prioritized default; Sonnet is reserved for units needing Claude-session-internal capabilities (MCP/email tools, Artifacts, cross-vendor web verification), with the orchestrator deciding per unit. Units may read or write code; workers never c
Passed 18 of 20 test cases with the skill, and 3 of 20 without it.
and 22 more in the full report
16 fixed2 passed either way1 still failing1 broke4 errored
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
One of 16 test cases the skill fixed. Same model, same prompt, with and without the skill.
A dispatch was launched with no model specified. The Gemini quota bucket has 40% remaining, while the secondary Claude Sonnet bucket has 70% remaining. Which model does `dispatch-task-agy.py` route the unit to, and what threshold triggers this switch?
| Checked | Without skill | With skill |
|---|---|---|
| Switches to Claude Sonnet because its remaining quota is at least 15 points higher. | Missed | Passed |
The instructions your model reads when the skill loads.
prun fans a task out into independent units that run in parallel while the current session only
coordinates. Every worker is an Agy process running Gemini through the Antigravity CLI, on the
Google AI plan authenticated in agy. The coordinator decomposes the task, dispatches the units,
gathers their results, reviews their diffs, and integrates. It never runs a unit itself.
No Claude-side workers. A Sonnet subagent, a Workflow agent, or any other Agent-tool worker draws
on the same Claude account as the coordinating session, so a fan-out of them spends that account's
quota at the rate of the fan-out. That is the pool the coordinating session itself needs, and it
drained fast once prun routed units to Sonnet. Codex is not a prun executor either; its
higher-cost quota is reserved for the default /vet gatekeeper role. Exact plan buckets can change,
so inspect current Agy quota before a large batch.
The native Workflow tool fans a task out across Claude subagents under a deterministic script, with structured output, judge panels, and resume. A Workflow run counts against the Anthropic plan's usage and rate limits, and its agents use the session model unless the script routes a stage to a different Claude model.
prun is the fan-out that stays off that account. Its units run on Agy and use the Google AI plan;
the coordinating session spends only the small Anthropic amount it needs to decompose, dispatch,
read results, and integrate. prun therefore never starts a Workflow or a Claude subagent, not as a
unit, a fallback, or a second panel. When the user explicitly asks for a Claude panel, that is a
Workflow run the user asked for, and it happens outside prun. A cross-vendor read on staged work
is what /vet is for.
When the Agy Gemini group cannot accommodate the next batch, queue or defer units instead of moving
them onto the Claude account. Read the meter with agent-quota, including snapshot age and reset
times, and do not silently shrink a genuinely parallel task to an arbitrary two or three workers.
The dispatcher's own quota route, described under dispatch-task usage, already stops a unit from
launching into an empty group.
Use prun when the task splits into independent units that can run at once (different
modules, separate research questions, parallel analyses). Units may be heterogeneous, and there
test cases passed, vs 3 / 20 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.