A structured workflow for AI coding agents. Drop it into any project, set your rules once, and stop re-explaining your codebase every chat.
This repository also configures its own agents. See what chief tells them →
Agent Claude Code
DEPRECATED — prefer answer-verifier-agent, which covers the same use cases and is actively wired into /chief-grill. Kept for backward compatibility with existing installs. Reviews plans, specs, and decisions for internal consistency and alignment with prior discussion. Catches contradictions between what was agreed in…
Agent Claude Code
Verifies a single grill-session answer against the codebase. Reads files, checks claims, surfaces contradictions or unfounded assumptions. Invoked per-question by /chief-grill (in the background) to cross-reference the user's latest answer with actual repo state. Returns a structured verdict the skill renders as a…
Agent Claude Code
Fast execution agent responsible for implementing tasks assigned by chief-agent. Reads: task specification for the assigned milestone global coding standards (.chief/rules/standard) Performs autonomous fix loops for implementation fallout (type/lint/test issues). Escalates only when blocked by design ambiguity…
Agent Claude Code
Goal-driven Planner/Orchestrator for the Chief Agent Framework. Reads AGENTS.md (highest priority), then .chief/rules, then milestone-specific goals. Produces and maintains milestone plans (plan/todo.md + task specs), delegates execution to builder-agent, delegates verification to tester-agent, and decides next…
Agent Claude Code
Long-running verification agent responsible for non-deterministic, integration, API, UI, and external acceptance testing. Executes medium-to-long duration validation tasks that go beyond local deterministic verification. Does NOT implement features. Does NOT refactor code. Reports findings back to chief-agent.…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: