A governed, portable engineering platform for coding agents: the governance layer (agentic-os), the SDLC pipeline that runs on it (agentic-sdlc), and a Quality Engineering blueprint catalog (agentic-qe).
Agent
Dispatch codebase-scout before any complexity scoring or brainstorming phase runs, whenever the pipeline needs grounded, read-only facts about the existing codebase rather than assumptions. It never plans or writes implementation code — its only output is a single technical-analysis.md research artifact that…
Agent
Use this agent when a feature branch has introduced structural or architectural changes and the guide corpus under .agentic/guides/ needs to be checked for drift. It is the standard dispatch target for mr-watch immediately after a merge lands, and repo-guides also points to it whenever ongoing sync against the guide…
Agent
Dispatch this agent whenever the gate-arbiter needs an autonomous stand-in tech-lead judgment at one of the three gates it owns: spec.approved, plan.approved, or qa.drift. It runs after the router's own deterministic pre-checks (evidence-file shape, per-task test-first declaration format) have already passed, and it…
Agent
Dispatch this agent whenever a task's size is not obvious from cheap heuristics and the orchestrator needs a defensible, six-dimension complexity score plus a routing call (plan directly vs. brainstorm first vs. split before planning). It never designs or writes code — it reads what earlier phases already learned…
Agent
Use this agent when gate-arbiter dispatches a requirements.ambiguous or spec.clarification judgment gate during an autonomous SDLC run and no human is available to answer synchronously. story-proxy resolves the open question by applying a fixed, priority-ordered rule set against the original task, supplied artifacts…