getting-started

An onboarding guide for Elliot, a platform that turns APIs and databases into tools for AI agents. It explains how to check the Elliot connection, understand the workflow, and choose the next step.

In plain words
What is it for?
Use it when starting work with Elliot or when an Elliot tool call fails because of a connection problem. It directs the agent to check session state and follow the platform’s connector-building workflow.
Why use it?
It helps diagnose common setup problems such as an unreachable or unauthorized Elliot server before connector work begins. It also provides the basic principles and sequence for using the platform.

Skill for Claude CodeCodex

Part of the elliot plugin — 10 skills, 2 hooks, 1 MCP server shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/elibarak12/elliot/getting-started
Any agent
npx skills add EliBarak12/Elliot --skill getting-started
Clone the repo
git clone --depth 1 https://github.com/EliBarak12/Elliot

Made for: Claude Code, Codex.

Or install elliot, the plugin that ships this one along with the rest of its 10 skills, 2 hooks, 1 MCP server.

Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,136 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00073 $0.02136
Opus 5 $0.00036 $0.01068
Sonnet 5 $0.00015 $0.00427
Haiku 4.5 $0.00007 $0.00214

Measured 3d ago against content hash 450cd350230a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

getting-started scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/getting-started/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Elliot — Getting Started

You are working with Elliot, a platform that turns existing APIs and databases into agent-ready MCP connectors. Your job is to help the user design, validate, deploy, and observe agent-ready tool sets built around their data sources.

⚠️ PREREQUISITE — can you reach the Elliot endpoint?

By default the marketplace wires your agent to the hosted Elliot Cloud builder at https://api.elliot-cloud.com/b/mcp. It's OAuth-protected, so the first tool call opens a browser tab to authorize Elliot Cloud — until that's done, calls come back unauthorized. If you run Elliot locally instead, the URL is your own (e.g. http://localhost:3000/mcp/) and that stack must be up. Either way, if the endpoint can't be reached every Elliot tool call fails — always check this first, because most "Elliot isn't working" problems are just an unreachable or unauthorized endpoint.

Quick check

Try calling elliot_get_session_state. Three possible outcomes:

Outcome What it means What to do
Returns a result with counts Endpoint is reachable ✓ Skip to the workflow section below
MCP transport error / connection refused Endpoint isn't reachable Help the user reconnect (next section)
tools/list doesn't include any elliot_* tools Plugin isn't installed at all Tell the user to run /plugin install elliot@elliot first

elliot_get_session_state returns counts of sources / tools / skills plus connector_built and runtime_running — it's the canonical "what's in this session" probe. (elliot_session_summary and studio_get_connector_info exist as thinner / Studio-flavoured variants of the same idea.)

If the endpoint isn't reachable, tell the user

Stop and help the user reconnect. If they're on Elliot Cloud (the marketplace default), use this message:

"I can't reach the Elliot Cloud builder at https://api.elliot-cloud.com/b/mcp. If a browser tab opened asking you to authorize Elliot Cloud, please complete that sign-in; otherwise check your network connection and that your Elliot Cloud account is active. Tell me when to retry."

Read the full file on GitHub · 128 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 128 lines · 73 tokens per session scan A 450cd350230a

Subscribe to this mod's changes

getting-started is a skill published in the GitHub repository EliBarak12/Elliot (11 stars, last pushed 6d ago), licensed MIT. It adds 73 tokens to every session and 2,136 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.