Six specialized agents. Each has its own model configuration, tool access, and a SOUL.md that defines precisely what it does — and what it must never do.
The only agent the user speaks to directly. Decomposes tasks, routes to the right Daimon, and synthesizes results. Owns .eter/.hermes/.
Maintains CURRENT.md and LOG.md. Detects blockers before they stop work. Provides session onboarding status on every open.
Receives specs from Hermes, spawns atomic sub-agents (Ergates) via delegate_task(role=...), consolidates results, and runs tests.
Uses web_search + web_extract. Every finding requires a source URL and a confidence level. Output is always structured: Findings / Sources / Confidence.
Designs user flows, layout specs, and HTML/CSS prototypes. Performs UX review post-implementation to catch regressions. Ensures WCAG compliance.
STRIDE threat modeling, OWASP review, dependency CVE auditing. Flags risks to Ariadna as sprint blockers. Activates proactively on new endpoints or dependencies.
At a glance — each Daimon's role, model, key tools, and SOUL.md limits.
claude-3.5-sonnetgpt-4oclaude-3.5-sonnetclaude-3.5-sonnetclaude-3.5-sonnetclaude-3.5-sonnet