# Quickstart: agents (SKILL.md)

Jell is built to be called by agents. The integration is one file: [`SKILL.md`](/SKILL.md) teaches an agent the MCP tools, the CLI, the HTTP interface, the spending rules (inspect before run, cap with `max_cost`, ask before batches over about $1) and which workflow skill to load for a whole GTM job.

## One-line install

Tell your agent:

```text
Set up https://jell.run/SKILL.md
```

The skill contains its own install instructions, so the agent persists it in the right place for its harness:

| Platform | Where the skill lives |
| --- | --- |
| Claude Code | `~/.claude/skills/jell/SKILL.md` (all projects) or `.claude/skills/jell/SKILL.md` |
| Codex | one pointer line in `AGENTS.md` (or `~/.codex/AGENTS.md`) |
| Cursor | `.cursor/rules/jell.mdc` |
| Gemini CLI | one pointer line in `GEMINI.md` |
| Cline | one pointer line in `.clinerules` |
| GitHub Copilot | one pointer line in `.github/copilot-instructions.md` |
| OpenClaw | `~/.openclaw/skills/jell/SKILL.md` |
| Hermes | `skills/jell/SKILL.md` in the workspace |
| Anything else | wherever persistent instructions live, or a one-line pointer to the SKILL.md URL |

Then connect the agent to your workspace. Two ways:

- **OAuth through the MCP server**, no key to handle. Claude Code: `claude mcp add --transport http jell https://api.jell.run/mcp`, then `/mcp` and **Authenticate**. Codex: `codex mcp add jell --url https://api.jell.run/mcp`, then `codex mcp login jell`. claude.ai and ChatGPT: add the URL as a connector. Each opens a Jell page where you sign in (password, Google, GitHub, or an emailed code) and approve a workspace. Details in the [MCP quickstart](/docs/quickstart-mcp).
- **A key**, for agents without a browser or without MCP (OpenClaw, Hermes, CI, a script, an agent built on the Claude or OpenAI API): mint one on the [dashboard](/dashboard) under API keys, and the agent stores it with `jell keys add -k <key> -l main` or sends it as the Bearer token over HTTP. Never commit the key.

The skill tells the agent to check for an existing MCP connection or stored credential before asking you for anything, and to verify access with the free `balance` call.

## Docs your agent can read

Every page of this documentation has a markdown twin at the same URL plus `.md` (this page: [`/docs/quickstart-agents.md`](/docs/quickstart-agents.md)), and [`/docs/llms.txt`](/docs/llms.txt) indexes them all. The site-wide index at [`/llms.txt`](/llms.txt) covers the catalog, providers and pricing.

So an agent needs no scraping and no browser: fetch `llms.txt`, follow the markdown, call the API.

## Two tiers, one loop

`discover` returns capabilities and raw endpoints together, ranked, with `hints` that say when a capability wraps the endpoint an agent found. The skill teaches the agent to prefer the capability (normalized output, a quote, failover) and to go one tier down only when it needs a provider field the catalog does not expose. [Raw endpoints](/docs/api/endpoints) has the full rules.

## MCP

Prefer native tools over a skill file? [Connect the MCP server](/docs/quickstart-mcp) at `https://api.jell.run/mcp`: discover, inspect, run, batch_run, runs, get_run, history and balance as MCP tools. Claude Code, Codex, claude.ai and ChatGPT authenticate with OAuth in the browser; other clients send the same key as a header.

## Spending rules the skill enforces

- Always `inspect` before the first run of a call: the schema and the price come from there, never from a guess.
- Respect `routing.max_cost` on every call, and set it on every raw endpoint run: with no quote, it is the only price control before the call.
- Stop and ask when a batch would exceed about $1.
- Report costs when they matter: when the user asked about price or set a budget, and as a total (the sum of each run's `billing.charged`) after a multi-run job.
- Never present sandbox mock data as real data.

## Next

- [Quickstart: CLI](/docs/quickstart-cli): the commands the agent will run.
- [API overview](/docs/api/overview): the HTTP surface behind them.

## Questions this page answers

### How can I add lead enrichment tools to my agent with a SKILL.md or MCP instead of writing wrappers?

Point the agent at `https://jell.run/SKILL.md`. The skill teaches it the CLI and the HTTP interface, so `contact.find`, `contact.verify`, `company.enrich`, `people.search` and the rest of the catalog become things the agent can run, with the price quoted first and one balance behind them. If your harness speaks MCP, the [MCP quickstart](/docs/quickstart-mcp) gives it the same catalog as native tools. Either way there is no wrapper to write per provider.

### Which agents does the SKILL.md work with?

Claude Code, Codex, Cursor, Gemini CLI, Cline, GitHub Copilot, OpenClaw, Hermes and anything else that reads persistent instructions: the table above lists where the file lives for each. The skill is a plain markdown file following the Agent Skills convention, and the [open-source skills repo](/skills) adds workflow skills (cold email pipeline, hiring-signal outbound, AI visibility audit, brand mention sweep) on top of the core one.