cupcake: Instructions file for Claude Code

Cupcake System Overview

• Function: A policy engine for AI coding agents (like Claude Code, Cursor, OpenCode) that intercepts tool calls, evaluates them against user-defined OPA Rego policies, and returns Allow, Block, or Warn decisions.
• Core Flow: $$\text{Event Input} \rightarrow \text{Route (O(1))} \rightarrow \text{Gather Signals} \rightarrow \text{Evaluate (WASM)} \rightarrow \text{Synthesize} \rightarrow \text{Response}$$
• Hybrid Model: Rego (WASM) declares rules/aggregates verbs; Rust (Engine) handles routing, signal gathering, and final decision synthesis.
• Two-Phase Evaluation:
  1. Phase 1 (Global Policies): Evaluated first (early termination on block). Organization-wide governance from ~/.cupcake/rulebook.yml.
  2. Phase 2 (Project Policies): Evaluated only if Phase 1 allows. Project-specific rules from .cupcake/rulebook.yml.

Policy Engine (WASM/Rego) Details

1. Routing vs. Policy Execution (CRITICAL)

• Routing is an optimization layer, not a selector.
  • Controls: Early exit if no policies match event criteria, and which signals to collect.
  • Does NOT Control: Which Rego rules execute inside WASM. All compiled policies run via the single entrypoint cupcake.system.evaluate.
• Policy Self-Filtering (MANDATORY): Policies MUST include event and tool checks in their Rego logic.

  deny contains decision if {
      input.hook_event_name == "PreToolUse"  # REQUIRED
      input.tool_name == "Bash"               # REQUIRED
      # ... your logic
  }
  

2. OPA Rego v1 Migration (CRITICAL)

Cupcake uses OPA v1.71.0+ where Rego v1 is the default syntax.