← ClaudeAtlas

shiplisted

Run parallel pre-launch review with code-reviewer, security-auditor, and test-engineer, then synthesize a go/no-go decision.
Saturate/agents · ★ 0 · Code & Development · score 66
Install: claude install-skill Saturate/agents
# Ship `/ship` is a **fan-out orchestrator**. It runs three specialist agents in parallel against the current changes, then merges their reports into a single go/no-go decision with a rollback plan. ## Phase A - Parallel fan-out Spawn three subagents concurrently using the Agent tool. **Issue all three Agent tool calls in a single assistant turn so they execute in parallel.** Sequential calls defeat the purpose of this command. Each agent gets the staged changes or recent commits as context: 1. **`code-reviewer`** -- Five-axis review (correctness, readability, architecture, security, performance). Output the standard review template. 2. **`security-auditor`** -- Vulnerability and threat-model pass. Check OWASP Top 10, secrets handling, auth/authz, dependency CVEs. Output the standard audit report. 3. **`test-engineer`** -- Coverage analysis. Identify gaps in happy path, edge cases, error paths, and concurrency scenarios. Output the standard coverage analysis. Constraints: - Subagents cannot spawn other subagents. Do not let one persona delegate to another. - Each subagent gets its own context window and returns only its report. **Skip the fan-out only if all of the following are true:** the change touches 2 files or fewer, the diff is under 50 lines, and it does not touch auth, payments, data access, or config/env. Otherwise, default to fan-out. ## Phase B - Merge in main context Once all three reports are back, the main agent (not a sub-persona) synthesizes them: 1