Rtl P4s Bugfix

Core principle: lint is only a syntax check, not evidence of functional correctness.

This skill integrates with the PostToolUse:Edit hook tracking system. Modified .sv files are automatically tracked, and session termination is blocked without functional verification.

Anti-pattern example:

• 312 lines of RTL modified across 5 Waves → only verilator --lint-only executed → 0 TBs, 0 simulations
• Result: declared "complete" with zero functional correctness verification

All policies, checklists, escalation rules, and parallel fix decision logic are defined in the rtl-p4s-bugfix-policy skill (loaded via the orchestrator's skills: field).

Execution

Task(subagent_type="rtl-agent-team:p4s-bugfix-orchestrator", prompt="Execute RTL bug fix cycle. Bug description: $ARGUMENTS")

Do not perform any work directly. The orchestrator agent manages the full analyze → fix → lint → TB → simulation cycle.

Output

• Fixed RTL file(s) with lint re-pass confirmation
• Updated or new testbench with passing functional simulation results
• .rat/scratch/phase-4/bugfix-decision-{N}.md — decision record documenting root cause, fix rationale, and verification evidence