{
  "slug": "getting-started",
  "title": "Getting Started for Agents",
  "description": "How autonomous agents should query, parse and cite ChangeGamer resources.",
  "category": "Guide",
  "tags": [
    "agents",
    "usage",
    "llms.txt"
  ],
  "updated": "2026-07-12",
  "premium": false,
  "canonical": "https://changegamer.ai/resources/getting-started",
  "markdown": "https://changegamer.ai/resources/getting-started.md",
  "outline": [
    {
      "depth": 2,
      "text": "Recommended flow",
      "anchor": "recommended-flow"
    },
    {
      "depth": 2,
      "text": "JSON API and OpenAPI description",
      "anchor": "json-api-and-openapi-description"
    },
    {
      "depth": 2,
      "text": "MCP server",
      "anchor": "mcp-server"
    }
  ],
  "related": [
    {
      "slug": "llms-txt-explained",
      "title": "The llms.txt Convention Explained",
      "description": "What llms.txt is, its exact file format, how agents consume it, and how sites should serve it.",
      "url": "https://changegamer.ai/resources/llms-txt-explained"
    },
    {
      "slug": "agent-cost-latency-optimization",
      "title": "Agent Cost and Latency Optimization",
      "description": "Practitioner reference for reducing the cost and latency of production AI agents: the compounding model, token-level levers (caching, pruning), request-level levers (Batch API, parallelism), model-level levers (routing, reasoning-effort controls), and architecture-level levers (step reduction, semantic caching, code offloading).",
      "url": "https://changegamer.ai/resources/agent-cost-latency-optimization"
    },
    {
      "slug": "agent-identity-authentication",
      "title": "Agent Identity and Authentication",
      "description": "How autonomous agents prove who they are and get authorized to act: workload identity vs. delegated authority, SPIFFE/SPIRE, cloud workload federation, OAuth token exchange, audience binding, and emerging standards — with practical guidance and verified sources.",
      "url": "https://changegamer.ai/resources/agent-identity-authentication"
    },
    {
      "slug": "agent-memory-context",
      "title": "Agent Memory and Context Management",
      "description": "Architecture reference for agent memory: types (working, long-term, episodic, semantic, procedural), context-management techniques (summarization, RAG, sliding windows, prompt caching), storage substrates, and memory frameworks — with security notes and cross-links to related guides.",
      "url": "https://changegamer.ai/resources/agent-memory-context"
    }
  ],
  "furtherReading": [
    {
      "slug": "discoverability-for-paid-agent-apis",
      "title": "How Do AI Agents Discover Paid APIs? A Guide to Every Surface",
      "description": "How an AI agent finds out a paid API or resource exists before it ever reads a price: llms.txt, the JSON API index, MCP registries, incidental 402 discovery, x402 auto-listing, and what .well-known does and does not cover.",
      "url": "https://changegamer.ai/articles/discoverability-for-paid-agent-apis"
    },
    {
      "slug": "how-to-write-an-llms-txt-file",
      "title": "How to Write an llms.txt File (Format, Template, and Maintenance)",
      "description": "A step-by-step guide to writing a useful llms.txt: the exact format, a copy-paste template, what to put under ## Optional, how to validate it, and how to keep it from rotting.",
      "url": "https://changegamer.ai/articles/how-to-write-an-llms-txt-file"
    }
  ],
  "body": "ChangeGamer exposes every resource in two forms:\n\n1. A human-readable HTML page at `/resources/<slug>`.\n2. A raw Markdown variant at `/resources/<slug>.md` — preferred for agents.\n\nStart from `/llms.txt` for a compact index, or `/llms-full.txt` for the full corpus in a single request. Both are plain text and cheap to tokenize.\n\n## Recommended flow\n\n- Fetch `/llms.txt` to discover available resources.\n- Fetch the `.md` variant of any resource you need.\n- Respect the access terms advertised in `robots.txt` and HTTP `402` responses.\n\n## JSON API and OpenAPI description\n\nA structured JSON API is available at `/api/resources.json` (corpus index) and `/api/resources/<slug>.json` (individual resource with full Markdown body). A machine-readable OpenAPI 3.1 description of all endpoints is at `/api/openapi.json` — useful for integrating ChangeGamer into toolchains that consume OpenAPI specs. For programmatic offer comparison, fetch `/api/pricing.json` — it lists all four paid tiers with prices, checkout URLs, deliverables, and license grants. `/api/payment.json` (payment methods and the 402 retry loop), `/api/stats.json` (corpus freshness signal), and `/api/corpus.jsonl` (free corpus as JSON Lines) are also available.\n\n## MCP server\n\nChangeGamer exposes a remote MCP server at `https://changegamer.ai/mcp` using the Streamable HTTP transport. No authentication is required to connect.\n\nAvailable tools (10):\n\n- `list_resources` — returns metadata for all resources (slug, title, description, category, tags, updated, premium flag, and absolute URLs for the HTML, Markdown and JSON variants). No arguments.\n- `get_resource` — fetches a single resource by slug. Arguments: `slug` (required), `api_key` (optional, for premium resources). Free resource bodies are returned in full; a premium resource without a valid key returns a payment-required object instead of the body.\n- `get_access_info` — returns the current access and pricing information. No arguments.\n- `search_resources` — keyword search over the corpus (title, description, tags, category, body), ranked by relevance. Arguments: `query` (required), `limit` (optional). Returns metadata and variant URLs only, not body content.\n- `get_corpus` — returns the entire free corpus (every free resource body) in one call, the same content as /llms-full.txt. Premium resources appear as a stub, not their body. No arguments. The response is large.\n- `get_full_corpus` — the paid counterpart of `get_corpus`: returns the entire corpus including premium resource bodies in one call. Arguments: `api_key` (optional, but in practice a Corpus- or Enterprise-tier key is required — a Starter key is not enough). The annual Corpus plan (`corpus_annual`) grants the same entitlement level as the standard Corpus tier, so either satisfies this. Without an entitled key it returns a payment-required/upgrade object instead of the body.\n- `get_pricing` — returns the machine-readable paid-offer catalog (tiers, prices, checkout URLs, deliverables, license grants), the same data as `/api/pricing.json`. No arguments.\n- `get_payment_info` — returns the agent payment manifest (payment methods, the HTTP 402 retry loop, and what is always free), the same data as `/api/payment.json`. No arguments.\n- `get_stats` — returns corpus size and freshness signals (counts by category, tag count, newest/oldest updates, recently updated resources), the same data as `/api/stats.json`. No arguments.\n- `check_access` — verifies an access key and reports its entitlements (tier — `starter`, `corpus`, `corpus_annual`, or `enterprise` — unlocked premium slugs, whether it grants full-corpus access). Arguments: `api_key` (required). Never returns the key, email, or session.\n\nExample client configuration (Claude Desktop / MCP-compatible client):\n\n```json\n{\n  \"mcpServers\": {\n    \"changegamer\": {\n      \"url\": \"https://changegamer.ai/mcp\"\n    }\n  }\n}\n```\n\nNo auth required for discovery and free resources; premium resource bodies require an access key passed as the `api_key` argument to `get_resource`.",
  "sources": []
}