Skip to main content
T3N ADK is Terminal 3’s SDK for building AI agents that can prove who they are, act only on scoped, revocable permission a user actually granted — never a standing API key — and take real-world actions like payments or payroll, all without exposing sensitive information to the model, the application, or the agent runtime (see What is T3N ADK? and Why T3N ADK? for the full picture). If you’re building your integration with an AI coding assistant, you don’t need to paste this whole documentation site into your context window. Drop the skill file below into your project and the assistant will follow the same order this documentation does: scaffold the project correctly, get a basic authenticated connection working before touching contract code, and check a known-pitfalls table before guessing at a fix.

Install it

Save the file below as .claude/skills/t3n-adk-quickstart/SKILL.md in your project (or your global ~/.claude/skills/ directory), then invoke it with /t3n-adk-quickstart or just describe what you’re building — Claude Code will pick it up automatically based on the skill’s description.

Self-service agent credit funding

T3nClient’s createAgent method (via its initialCredits option) and its fundAgent() method (confirmed live on testnet, @terminal3/t3n-sdk 5.16.0+ — see the Changelog) let a developer fund an agent’s T3N credit balance without asking a cluster operator (Terminal 3’s own ops team). Both are called on the authenticated client (t3n.createAgent(...), t3n.fundAgent(...)) from Step 3 above, not imported as standalone functions. The authorization model behind them is easy to get wrong on a first read, and most of the confusion isn’t in the API shape — it’s in why a call gets refused. The two prompts below encode that model as explicit rules so your assistant can reason about a refusal correctly the first time, rather than guessing from the error text alone. Same install mechanism as the skill file above — save the Claude-flavored one as a Claude Code skill (or append it to the skill above), and the OpenAI-flavored one as a system prompt / project instructions file for an OpenAI-family assistant.

FAQ

A single Markdown file (Claude Code Skill frontmatter + instructions) that teaches an AI coding assistant the exact order to scaffold, connect, and debug a T3N ADK integration — including the known-pitfalls table above. It’s not documentation to read; it’s meant to be dropped straight into a project so the assistant follows it automatically. See Install it above for the exact file to save per tool.
Claude Code natively (as a Skill), Codex (saved as AGENTS.md), Cursor (saved as .cursorrules), and Windsurf or any other tool that accepts a plain system-context/rules file — see the tabs under Install it.
No. The skill file only teaches the assistant how to call the SDK correctly — it doesn’t change what the assistant can see at runtime. Real user data (PII, credentials) is substituted inside the TEE via placeholder markers, so a contract, and anything inspecting or logging it, only ever sees the placeholder, never the plaintext value — it never ends up in the model’s context window, a chat log, or your own application logs either. See Placeholders in outbound calls and the ADK Tour.
Yes — an agent only gets whatever specific functions and external hosts a user explicitly delegates to it; there’s no broader standing access to fall back on. See Member Delegation for how a user grants that scope, and Outbound HTTP calls are authorized by the user, not the contract for exactly what an agent can and can’t reach as a result.
It’s contained by the same delegation model: an agent never has standing access to anything, so a compromised or misbehaving agent can still only reach what was explicitly delegated to it — no grant, no access. The contract still runs, but any call outside what was actually authorized is simply refused (host/http.egress_denied), not silently allowed — see Outbound HTTP calls are authorized by the user, not the contract for what that refusal looks like in practice.
Yes — see This documentation is agent-readable too below. The skill file is the fast path for building; the raw Markdown pages and /llms.txt index are there for open-ended exploration or questions the skill file doesn’t cover.

This documentation is agent-readable too

Every page on this site is available as plain Markdown by appending .md to its URL, and a machine-readable index of every page lives at /llms.txt — point an agent there if you want it to explore the docs directly instead of relying on the skill file above.

SDK & API Reference

If you’re pasting context manually instead of using the skill file, this single page is the highest-value one to include — every confirmed method, host interface, and API tag in one place.