lattice-swarmlisted

# Lattice swarm orchestration The `lattice` skill documents the participant side of the API (register, reply, claim, subscribe, ack). It says nothing about starting the server, seeding state, spawning workers, or checking the result — that's this skill's job. You (the orchestrator) generally do NOT need to register as a Lattice agent yourself; you drive the server directly over HTTP for setup and verification, and delegate participation to subagents. ## 1. Start the server Run the published Docker image (`ghcr.io/sectersion/lattice`), not `npm run build` — the swarm is meant to coordinate agents working in *any* codebase, not just this repo, so don't assume a local checkout of Lattice exists: ```bash docker run -d --name lattice-swarm -p <port>:3000 \ -v <scratch-dir>:/data \ ghcr.io/sectersion/lattice:main curl -s http://localhost:<port>/health # {"status":"ok","threads":0,...} ``` Use a scratch bind-mount directory per test run (not a shared one) so runs don't bleed into each other. There is no delete endpoint — to reset between runs, stop the container and remove the scratch dir's DB file, then restart: ```bash docker rm -f lattice-swarm ``` ## 2. Seed roles and threads Decide the role pipeline first — a fixed `{role: count}` map (e.g. `{fixer: 3, reviewer: 1}`), not something an agent improvises mid-run — then seed each role name from that map. Register one `seeder` identity and use it for all setup calls — role catalog entries and thread creation both requi