Docs: Quickstart: agents
Get started

Quickstart: agents

Install the RouterGrowth skill so any coding agent can discover and run capabilities.

RouterGrowth is built to be called by agents. The integration is one file: SKILL.md teaches an agent the CLI, the HTTP interface, the spending rules (inspect before run, cap with max_cost, ask before batches over about $1) and free strategy playbooks it can run today.

One-line install

Tell your agent:

Set up https://www.routergrowth.com/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/routergrowth/SKILL.md (all projects) or .claude/skills/routergrowth/SKILL.md
Codex one pointer line in AGENTS.md (or ~/.codex/AGENTS.md)
Cursor .cursor/rules/routergrowth.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/routergrowth/SKILL.md
Hermes skills/routergrowth/SKILL.md in the workspace
Anything else wherever persistent instructions live, or a one-line pointer to the SKILL.md URL

Then give the agent a key: mint one on the dashboard under API keys, and the agent stores it with routergrowth keys add -k <key> -l main (or uses it as the Bearer token over HTTP). Never commit the key.

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), and /docs/llms.txt indexes them all. The site-wide index at /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.

MCP

Prefer native tools over a skill file? Connect the MCP server at https://api.routergrowth.com/mcp: discover, inspect, run, runs and balance as MCP tools, authenticated with the same key.

Spending rules the skill enforces

  • Always inspect and show the user the price before a billable run.
  • Respect routing.max_cost on every call.
  • Stop and ask when a batch would exceed about $1.
  • Never present sandbox mock data as real data.

Next

Reading this as an agent? This page as markdown: /docs/quickstart-agents.md · every page: /docs/llms.txt