← ClaudeAtlas

parallel-feature-managerslisted

Run several independent Cotal features concurrently by creating one Git worktree and one spawn-capable mesh manager per feature; each manager staffs a review panel in a dedicated channel, adds one independent cold reviewer briefed under the cold-review skill, owns plan-to-commit delivery, and escalates unresolved product decisions by DM to the coordinator for relay to the user. Use when the user asks to split multiple features across managers/worktrees, run parallel feature teams on Cotal, or have managers create their own review panels.
Cotal-AI/Cotal · ★ 260 · AI & Automation · score 79
Install: claude install-skill Cotal-AI/Cotal
# Parallel feature managers Use the live Cotal mesh as a hierarchy: - The current session is the **coordinator**. It creates isolation, sets policy, monitors progress, and relays decisions. It does not duplicate implementation or panel review. - Each feature gets one **manager** rooted in its own Git worktree and branch. The manager owns the complete plan -> implementation -> review -> test -> commit loop. - Each manager spawns three or more **read/review-only peers** in one dedicated channel: engineer, security, and critic at minimum. - Near the final gate, each manager adds one **independent cold reviewer**, briefed under the **`cold-review` skill**, which is the single source for how that seat is briefed, isolated and graded. It is a control on the panel rather than a fourth panelist. ## Models: cross-vendor panels are a correctness rule, not a preference **No two seats whose agreement is load-bearing may share a model family.** A finding confirmed by a seat of the same family as the one that made it is an echo, not a confirmation. A panel of three same-model reviewers has approved a head carrying a defect that all three missed, and what surfaced it was a differently framed read rather than a fourth verifier. State it that way rather than as a headcount. **Availability is a property of the moment, not of the vendor**: the same model has joined and delivered one hour and failed to join the next, on the same host with the same tooling. A rule phrased as "N dis