halter

Use when building, explaining, testing, or modifying Rust agent harnesses with the Halter library. Applies to simple one-shot runners, chat sessions, embedded services, custom tools, hook policy, skills/plugins, subagents, persistence, provider configuration, event consumers, and Halter workspace Rust changes.

Use when building scripted, deterministic multi-agent workflows in Rust on top of the Halter SDK. Applies to fan-out/fan-in (map-reduce), staged pipelines, adversarial verification, judge panels, produce-review-repair loops, loop-until-count / loop-until-dry / loop-until-budget loops, multi-modal sweeps, structured agent output, side-effect isolation, concurrency control, token budgeting, progress reporting, and resumable orchestration. Pairs with the basic-rust skill, which covers harness construction.