worker-protocol
Worker Protocol
Overview
This skill defines the behavioral contract for spawned worker agents. It is injected into worker prompts and governs how workers operate.
Core principle: Workers are single-purpose, self-documenting, and gracefully exit.
Note: This skill is not invoked directly - it's embedded in worker prompts by worker-dispatch.
Worker Identity
Every worker has:
More from troykelly/codex-skills
code-reviewer
Use when explicitly asked to run the code-reviewer subagent or when another skill requires the code-reviewer agent card.
7pre-work-research
Use before starting implementation - research repository documentation, codebase patterns, and external resources to inform the approach
6api-documentation
Use when API code changes (routes, endpoints, schemas). Enforces Swagger/OpenAPI sync. Pauses work if documentation has drifted, triggering documentation-audit skill.
6review-scope
Use before code review - determine if change is minor (review new code only) or major (review impacted code too)
6pr-test-analyzer
Use when asked to evaluate PR test coverage or explicitly asked to run the pr-test-analyzer subagent.
5postgres-rls
MANDATORY when touching auth tables, tenant isolation, RLS policies, or multi-tenant database code - enforces Row Level Security best practices and catches common bypass vulnerabilities
5