hstackfrontierThe senior engineer: intake, plan review, terse directives, final review, token discipline.
hstackSmall models do the work. Frontier models direct it. Agent skills that turn a cheap model into your engineering team and a frontier model into its senior engineer.
tsc and vitest pass. I'll review exact strings, diff hunks and cron weekday rules.tsc clean · 141/141 passing.How it works
About 20 lines: why, acceptance criteria, constraints, and the risks it will check. No spec, no code.
Writes the spec, plan and tests, builds alone or with 1 to N sub-agents, and runs an independent reviewer that tries to break it.
Wakes only when the plan or the result is ready, and answers APPROVE or a few lines of REVISE. Waiting costs nothing.

Benchmark 1 · six engine modules
The small model wrote 95% of the output for 10 cents. Exact token counts, including every sub-agent, and a hidden 82-test suite neither side saw.
The skills
hstackfrontierThe senior engineer: intake, plan review, terse directives, final review, token discipline.
hstack-leadsmall modelOwns the task end to end: spec, plan, fan-out, tests-first build, independent review, checkpoints.
hstack-practicesmall modelEngineering habits small models lack: exact specs, state tables, real-environment facts, security, honest reports.
Curated skills that make the small model better on its own: testing, security, frameworks, data and UI quality. The more it knows, the less the frontier has to correct.
The installer asks for your agent, your frontier model and your small model, then sets everything up. Muse Code today, more agents later.
curl -fsSL https://hstack.shellhaki.dev/install | shgo install github.com/shellhaki/hstack/cmd/hstack@latest && hstack/hstack-activate.