Universal guardrails loaded by every agent. Defines Verify Before Reporting (VBR), Write-Ahead Log (WAL), and the security baseline. Always-on, role-independent.
Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.
Records decisions and documentation. Use when making architectural decisions, changing public APIs, shipping features, or when you need to record context that future engineers and agents will need to understand the codebase.
Use when: Good night Team, EOD, Wrapping up, or end-of-day consolidation. Archives session context, promotes durable patterns, and compacts live agent memory files for the next session.
Review Codex/Claude agent skills, profile manifests, and skill-related deploy changes before they ship. Use when creating, editing, importing, installing, or reviewing SKILL.md files, agent manifests, optional third-party skills, or plugin skill bundles.…
Use when: ticket lifecycle, state transitions, ready for QA, changes requested, QA passed, role-based workflow policy, Developer to QA handoff, or relay routing across delivery agents.
Use when: architecture mode, architect this, ADR, C4, PlantUML, system boundary, design decision, PRD gap, high ambiguity, multiple technical approaches, security architecture, data architecture, integration risk, implementability gap, story ticket, or epic…
Token budgeting discipline for all agents. Treats tokens as a resource from session start — not just when the buffer hits 60%. Covers prompt compression, context hygiene, handoff packing, and HOT memory pruning.