Skills
What OKE ships to teach AI agents the system — the repo-level AGENTS.md contract and the installable skills under .agents/skills/.
Tools alone don't make a good operator — an agent also needs to know the vocabulary: what a Flow is, why fx is the only door, which driver ids are legal. OKE ships that knowledge as contracts and skills that agents load automatically, so sessions start aligned instead of drifting and getting corrected.
The three layers
| Layer | Path | Loaded when | Teaches |
|---|---|---|---|
| Agent contract | AGENTS.md (repo root) | Every agent session, automatically | The one law, eight elements, ten exports, the fx rule, ports, budgets |
| Element skill | .agents/skills/oke/ | Building or changing an okengine app | The element contract in depth — declaration patterns per element |
| Docs skill | .agents/skills/oke-docs/ | Writing or editing docs under site/content/docs | The documentation information-architecture standard and its gates |
AGENTS.md — the root contract
Every OKE app's repo carries an AGENTS.md that agents (Cursor, Claude Code, and peers) read at session start. It is deliberately short and absolute: every backend behavior is a Flow (on(Trigger) → Effects), there are eight elements and ten exports, all world access goes through fx, drivers are named after protocols, and the ports/budgets are fixed. Its closing rule is the one that keeps agents honest: if the documentation is silent, stop and ask — never invent the API.
Skills — installable know-how
Skills are SKILL.md packages an agent loads when the work matches their description. The two OKE ships:
| Skill | Use it for | Inside |
|---|---|---|
oke | App work — flows, elements, drivers | The agent contract, element patterns, the fx invariants |
oke-docs | Docs work — new pages, rewrites | The page skeleton, verification sources, the density gate |
Both live in the repo under .agents/skills/, so they travel with the code and stay versioned with what they describe.
How contracts compose with MCP
Contracts teach the vocabulary; MCP grants the hands. An agent that knows the eight elements from AGENTS.md reads the Manifest through oke.manifest.get with the right mental model — and its write attempts still pass through per-call human confirmation, because knowing the system is not the same as being trusted by it.
Learn more
- MCP — the runtime surface these contracts pair with
- Introduction — the eight elements in human terms
- llms.txt — feeding an agent the docs themselves
Next
MCP
The runtime MCP server on :6535 — read tools for Manifest, schemas, effects, and traces, write actions gated by per-call human confirmation — plus the read-only docs MCP on :6536.
llms.txt
Machine-readable documentation — the index, the full concatenated text, and per-page markdown endpoints this site serves for agents.