hstack-activatefrontierTurns hstack on and keeps asking for a worker model until you name a valid, smaller one. Loose names like "haiku 5.5" work.
Agent skills that make your frontier model a senior engineer and a cheaper model the engineer who does the work. Half the cost, same hidden tests.
curl -fsSL https://hstack.shellhaki.dev/install | shView the sourceBenchmark 2 · production waitlist backend · Claude Code
Same spec, separate Claude Code sessions. Opus 5.5 wrote 90% fewer output tokens. Costs are Claude Code's own per-model list-price figures, sub-agent included, judged by a 20-test suite neither side saw.
hstack is a set of skills and sub-agents. It runs inside the agent you already use, on the subscription you already pay for.
A real run from the benchmark: one brief, one approval, one correction, and no code from the frontier.
tsc and vitest pass. I'll review the rate limiter, CSV formula guard, cursor and signup check order.tsc clean · 199/199 passing.About 15 lines: why, acceptance criteria, constraints, the risks it will check, and the done commands. No code.
A sub-agent on a smaller model plans, writes tests first, builds, and reports. /hstack-swarm splits the work across parallel workers and a reviewer.
Approves the plan, runs the checks itself, spot-checks its risks, and sends at most one short correction. It never writes the code.

Plus two sub-agents, hstack-worker and hstack-reviewer, that the skills start on your worker model.
hstack-activatefrontierTurns hstack on and keeps asking for a worker model until you name a valid, smaller one. Loose names like "haiku 5.5" work.
hstackfrontierThe senior engineer: size gate, brief, plan review, build review, one correction round, token discipline.
hstack-swarmfrontierParallel workers on independent parts, then an independent reviewer that tries to break the result.
hstack-practiceworkerEngineering habits small models lack: exact specs, state tables, tests first, real-environment facts, security, honest reports.
Curated skills that make the worker better on its own: testing, security, frameworks, data and UI quality. The more it knows, the less the frontier has to correct.
go install github.com/shellhaki/hstack/cmd/hstack@latest && hstack