sisyphus

Forensic debugging of a past sisyphus multi-agent session — reconstruct what the orchestrator and each agent could see at each decision point and judge whether their calls were reasonable. Use when asked to debug, autopsy, or explain a sisyphus session: a failure, wasted cycles, a weird decision, a stalled agent, or how a session succeeded. Takes a session ID/name or a path to a session dir or exported dump.

Author new sisyphus agents, sub-agents, hooks, skills, and orchestrator modes. Use when extending sisyphus runtime behavior — adding a domain-specific agent variant, project-level hook, custom orchestrator phase, or shared skill. Covers what to put in each file, why, and which extension to reach for.

Project-local operational knowledge for THIS app, accumulated by prior operator runs. Covers app surfaces (routes, ports, processes, admin overlays), auth/login flow, db state management, common UI flows, and known footguns. Use whenever the operator agent needs project-specific operating knowledge — read at session start, update before submitting.

Runtime mental model, agent boundaries, and workflow patterns for the sisyphus multi-agent orchestration system