Instructions file GitHub Copilot
Instructions for hecatehq/hecate: Hecate is an open-source local AI operations console for supervised agent work. It combines a model gateway, Hecate Chat, queued agentloop tasks, External Agent supervision, projects, memory, approvals, artifacts, usage, and OpenTelemetry traces into one operator surface.
Instructions file GitHub Copilot
Instructions for hecatehq/hecate: Agent guidance is provider-neutral. Keep docs-ai/ as the source of truth and use adapter files only to help a specific product discover that guidance.
Instructions file GitHub Copilot
Instructions for hecatehq/hecate: For Go backend/runtime work, read AGENTS.md plus docs-ai/skills/backend/SKILL.md. Use docs-ai/core/verification.md for the verification ladder.
Instructions file GitHub Copilot
Instructions for hecatehq/hecate: For provider work, read internal/providers/AGENTS.md and docs-ai/skills/providers/SKILL.md before editing.
Instructions file GitHub Copilot
Instructions for hecatehq/hecate: For desktop work, read docs-ai/skills/tauri/SKILL.md before editing.
Instructions file GitHub Copilot
Instructions for hecatehq/hecate: For UI work, read ui/AGENTS.md and docs-ai/skills/ui/SKILL.md before editing.
Instructions file CodexOpenCode
Instructions for hecatehq/hecate, covering hecate, where guidance lives, codebase map, runtime invariants and conventions (in brief).
Instructions file
Instructions for hecatehq/hecate, a project described as: AI workspace and runtime for projects, chats, providers, memory, approvals, and supervised agents.
Skill Claude CodeCodex
Use when planning a substantial change before coding — new wire fields, new persisted things, new endpoints, new persistent UI surfaces, cross-package refactors. Produces a structured plan, not code.
Skill Claude CodeCodex
Use when working on the Hecate Go backend — gateway, agent runtime, providers, sandbox, storage. Keeps backend work aligned with Hecate's "operator-grade control plane, runtime-aware" thesis.
Skill Claude CodeCodex
Use when reviewing delivery safety — env-var changes, schema migrations, deploy risk, rollback paths, observability surfaces, release notes.
Skill Claude CodeCodex
Use for routine repo upkeep: recurring health checks, branch/worktree cleanup, stale docs or product-language drift, dependency drift review, and maintenance PR prep.
Skill Claude CodeCodex
Use when working in internal/providers/ — outbound HTTP adapters to LLM upstreams (OpenAI-compat, Anthropic). Owns the api↔providers parallel-struct boundary and the seven-step "add a wire field" chain.
Skill Claude CodeCodex
Use when working on the Hecate native desktop app in tauri/. Covers the Tauri 2.x Rust layer, sidecar lifecycle, platform bundling, and the gateway↔webview integration.
Skill Claude CodeCodex
Use when choosing test layers, designing regression coverage, auditing test gaps, or reporting verification results. Pushes for evidence, not assumptions.
Skill Claude CodeCodex
Use when working on the Hecate operator UI in ui/. Keeps frontend work aligned with Hecate's operator-console workflows, runtime-debugging focus, and React/Vite stack.