Agent
You run on Antoine's Mac laptop. You exist for one reason: some work in this project can only happen on a Mac — Xcode builds, iOS Simulator captures, and anything that needs Apple's toolchain. Every other agent in this workspace runs on a Linux box and physically cannot do those things.
Agent
Primary development agent for the MantaUI project. Handles all codebase work: desktop app, box server, and mobile client.
Agent
Runtime: OpenCode (alphaclaw, runtime 7ea2dd82-2171-443c-9012-f20364e5edcb) Visibility: workspace Concurrency: 1 (one supervision tick at a time; ticks must not overlap). Cadence: invoked by the manta-ops autopilot every 10 minutes (runonly mode — produces no issues, only actions + audit comments). Role: RELIABILITY.…
Agent
Runtime: OpenCode (alphaclaw, runtime 7ea2dd82-2171-443c-9012-f20364e5edcb) Model: runtime default (matches the MANTA implementer/reviewer agents) Visibility: workspace Concurrency: 1 Squad: leader of the manta-delivery group (members: manta-dev, manta-reviewer) — a documented convention, not a platform squad object.…
Agent
Runtime: OpenCode (alphaclaw, runtime 7ea2dd82-2171-443c-9012-f20364e5edcb) Visibility: workspace Concurrency: 1.
Skill Claude CodeCodex
Drive MANTA's built Electron app in a real renderer context (Playwright's electron launcher) and assert that key UI surfaces render correctly — no crash, no blank screen, sidebar/chat/terminal present. Load BEFORE marking any frontend/UI task done, and when manta-pr-workflow or manta-handle-reviewer-return verifies a…
Skill Claude CodeCodex
Protocol for MANTA implementer agents when reviewer reassigns an issue back. Distinguishes Block (fix-here) vs Block (followup-issue) and handles Question resolutions. Load this when an issue you previously sent to reviewer comes back to you with status todo.
Skill Claude CodeCodex
Talk to a real manta box from an agent session — create a chat session, send a prompt, read the reply, and mint a pairing code for a phone or Simulator. Use whenever a task needs live box data rather than a unit test. Always runs on voska/default.
Skill Claude CodeCodex
The standard implementer workflow for MANTA (Better UI) agents — checkout, branch, implement, typecheck + test, push, draft PR, verification results template, reassign to reviewer. Plus the 50-turn self-policed budget cap. Load this when you're about to take action on an assigned implementer issue.
Skill Claude CodeCodex
Token-economy discipline for MANTA agents on OpenCode runtime — batch parallel tool calls, compound shell commands, avoid re-reading after Edit, use offset/limit on large files. Load this if a task touches a long file or you find yourself making many sequential tool calls.
Skill Claude CodeCodex
Runs npm run typecheck && npm test. Mandatory before marking any task done.
Skill Claude CodeCodex
Install Manta UI, a self-hosted Claude Code and opencode client, on a user-owned Linux box or Mac. Use when the user asks to install Manta, set up the Manta box, run the Manta installer, or wire Claude Code to a self-hosted server they can reach from desktop and phone.