AI Agent Integration Guides
Use Assay's 51 modules in Claude Code, Cursor, Windsurf, Cline, and OpenCode.
How It Works
Your AI agent writes Lua scripts that use Assay's stdlib modules. Two ways to give your agent knowledge of the modules:
- SKILL.md — Download SKILL.md into your project. Most agents (Claude Code, Cursor) read it automatically.
assay context— Runassay context "<query>"to get LLM-ready module docs. Paste into your agent's chat.
# Get module docs for your AI agent
assay context "grafana" # monitoring module docs
assay context "kubernetes auth" # k8s module docs
assay context "vault secrets" # vault module docs
assay context "github prs" # github module docs
assay context "openclaw tools" # AI agent platform docs
Claude Code
Download SKILL.md
into your project and reference it from AGENTS.md. Claude Code reads
AGENTS.md automatically, giving it full knowledge of Assay's modules and patterns.
# In your project's AGENTS.md, add:
# For Assay module patterns, see SKILL.md
# Then use assay context for specific queries:
assay context "prometheus alerts"
assay context "argocd sync"
Cursor
Use assay context from your terminal and paste the output into Cursor's chat.
Cursor also reads .cursorrules or project docs.
assay context "prometheus" # monitoring module docs
assay context "argocd sync" # GitOps module docs
assay context "s3 storage" # S3 module docs
Windsurf
Run assay context from Windsurf's integrated terminal and paste output into the
AI chat panel.
assay context "traefik" # ingress/routing docs
assay context "certmanager" # TLS certificate docs
assay context "harbor registry" # container registry docs
Cline
Use assay context from VS Code's integrated terminal. Cline can read terminal
output when you paste it into the chat.
assay context "loki logging" # log aggregation docs
assay context "temporal workflow" # workflow orchestration docs
assay context "unleash flags" # feature flag docs
OpenCode / OpenClaw
Install the Assay skill directly into your project. For OpenClaw agents, use
assay.openclaw for native tool invocation, state management, and LLM tasks.
# Download SKILL.md into your project
curl -L -o SKILL.md https://raw.githubusercontent.com/developerinlondon/assay/main/SKILL.md
# OpenClaw agents can use the openclaw module natively:
local openclaw = require("assay.openclaw")
local c = openclaw.client()
c:send("discord", "#alerts", "Deploy complete!")
c:state_set("last-deploy", { version = "1.2.3" })
Quick Reference
| Agent | Best Integration |
|---|---|
| Claude Code | Add SKILL.md to project, reference in AGENTS.md |
| Cursor | assay context → paste into chat |
| Windsurf | assay context → paste into chat |
| Cline | assay context → paste into chat |
| OpenCode / OpenClaw | Install skill + assay.openclaw module |
Common Workflow
# 1. Find the right module
assay context "what you need"
# 2. Read the output — shows method signatures and return types
# 3. Write your Lua script:
local mod = require("assay.<module>")
local c = mod.client("http://service:port", { token = "..." })
local result = c:some_method()
assert.not_nil(result)
# 4. Run it
assay script.lua
All 34 stdlib modules follow the same pattern: require, client(),
c:method(). Learn one, know them all.
For LLM agents: llms.txt · llms-full.txt