Instructions file CodexOpenCode
Instructions for sixb-ai/sixb, covering agents.md, scope, repo map, toolchain and core commands.
Instructions file CodexOpenCode
Instructions for sixb-ai/sixb, covering agents.md, scope, repo map, toolchain and core commands.
Instructions file
Instructions for sixb-ai/sixb, a project described as: Open-source TypeScript framework for building operational software used by humans and AI agents.
Agent
Agents touch the same data and actions as everyone else, so the same authorization model governs them. Two things decide what an agent can do: the groups on its definition and the owner of each thread.
Agent
Agent "defining-agents" from sixb-ai/sixb, covering defining agents, config, the model, instructions vs agent skills and tools.
Agent
An agent is a conversational assistant you define alongside your ontology. It calls a language model, selected worker tools, sandboxed read and bash, and an authorized Sixb API.
Agent
A defined agent does nothing until a conversation drives it. You drive it over HTTP — create a thread, post a message, follow the run — and stream the run live over a websocket.
Agent
Every agent run gets sandboxed read and bash tools plus scoped access to the Sixb API. Agents may also receive explicitly selected tools that run in the agent worker.
Skill Claude CodeCodex
Use when requesting declared Sixb ontology actions as the preferred mutation path.
Skill Claude CodeCodex
Use when publishing a generated file as a Sixb FileRef for a declared action or workflow.
Skill Claude CodeCodex
Use when discovering ontology, reading Sixb objects, filtering, sorting, paging, counting, faceting, traversing links, or expanding object query results.
Skill Claude CodeCodex
Use when reading Sixb telemetry latest values or history for ontology telemetry properties.
Skill Claude CodeCodex
Use when discovering, starting, or monitoring authorized declared Sixb workflows.