eight-eyes vs. anticipating-shadow-points

Multi-agent code review with 8 hook-enforced roles. Each role targets a different failure surface — the skeptic reviews blind without the implementer's narrative, the security auditor can only run approved scan commands, the test writer cannot touch source code, and the implementer cannot run Bash. Scope boundaries are enforced through deterministic Python hooks at the PreToolUse layer, not through prompt instructions. The 8 roles: implementer (scoped writes, no Bash), test-writer (test directories only), skeptic (blind read-only review), security auditor (read-only + approved scan commands), performance profiler (benchmarks in isolated worktree), accessibility checker (a11y tools + WCAG 2.1 checks), docs writer (doc paths only), and verifier (approved verification commands only). Features include parallel audit phase (4 review agents run concurrently), TDD mode (hook-level test-first enforcement), custom roles via manifest (--custom-role), REVIEW.md injection for project-specific review criteria, mission tim

Helps you ship complex engineering work without missing the obvious. Before any code is written, ASP runs an automated pre-mortem to surface failure modes that engineers (and LLMs) routinely miss on first pass — RLS policy gaps, replica lag during migrations, rate-limit issues in external APIs, deprecated callsites, monitoring blind spots, untested rollback paths. It then validates the plan with an independent agent, locks execution into a step-by-step contract with acceptance tests, and runs autonomously until done. Use before any non-trivial task: schema migrations, refactors across many files, deploys with external dependencies, RLS policy changes, or architecture decisions. Multilingual docs (English, Spanish, Portuguese, Italian, Hebrew). MIT licensed.