adversarial-planner

Adversarial Planner

A multi-pass planning and review system that produces high-quality plans by introducing structured adversarial critique stages. Plans pass through an iterative pipeline of drafting, review, refinement, and optional external validation — producing output optimized for correctness, performance, security, and maintainability.

When to Load

Load this skill when any of these apply:

• Creating an implementation plan for a new feature or architectural change
• Designing multi-file refactors or system migrations
• Planning project roadmaps, milestones, or sprint scopes
• The user asks for an adversarial or multi-pass review of a plan
• The user says "plan this", "review my plan", "critique this plan", "multi-pass plan", "architect this", "design this system", or "how should I build"
• You want to reduce confirmation bias in your own planning output

Adversarial Protocol

This skill follows the standard dual-agent adversarial pattern (Agent A: The Planner, Agent B: The Adversarial Reviewer). For the core pipeline rules, phase definitions, and agent switching protocols, read: ../adversarial-security/references/adversarial-base-protocol.md

For the planner-specific protocol with review dimensions, scoring weights, and output templates, read: references/multi-pass-protocol.md

External Validation (Phase 4)

Phase 4 triggers an independent validation pass using the GitHub CLI (gh copilot). The copilot subcommand is built into modern gh CLI — no separate extension is needed. This provides a fundamentally different model's perspective on the plan, reducing confirmation bias that persists even after adversarial self-review.

For Copilot-specific prompt templates and integration details, read references/copilot-integration.md.

Prerequisites: gh CLI v2.x+ with gh auth status passing. If gh copilot is not available, skip Phase 4 gracefully and note the skip in the journal entry.