name: x-agent-resources description: Integration and usage of official X Developer Platform agent resources (llms.txt, skill.md, MCP/XMCP, xurl, OpenAPI) for accurate, composable X access in agentic apps. Use when building search, analysis, posting, or any X interaction. Ensures llms/skill ground prompts, MCP exposes tools, xurl provides CLI UX. Fission for implementation; fusion for unifying with finder-reactor and agentic design.
X Agent Resources — Official Primitives for X-Powered Agents
Core Mission: Make every X interaction correct, efficient, and agent-composable by treating official X agent resources as first-class citizens.
Key Resources (Always Reference Fresh or Cached)
- llms.txt / llms-full.txt (https://docs.x.com/llms.txt): Structured index + full Markdown docs for LLMs.
- skill.md (https://docs.x.com/skill.md): agentskills.io spec — capabilities, actions, params, constraints, workflows.
- MCP Servers: XMCP (200+ endpoints as tools); Docs MCP.
- xurl (https://github.com/xdevplatform/xurl): Official CLI with auto-auth and agent SKILL.md.
- OpenAPI: https://api.x.com/2/openapi.json
Agent read order (mandatory for X work)
- Vendored snapshot in your project (e.g.
.agents/x-resources/skill.md) — read first. - This skill — integration patterns for your app.
- Live
https://docs.x.com/...if behavior disagrees with snapshot — refresh vendored copy.
Integration Principles
- Ingest for Intelligence: LLM calls include relevant excerpts from X skill.md + llms context.
- MCP for Composability: Expose app functions (search, analyze, prep, promote) as MCP tools; use XMCP for direct X ops when richer than a custom client.
- xurl for UX & Fallback: Shell to xurl for ad-hoc or as reference implementation.
- Follow the Spec: Publish your own SKILL.md compatible with agentskills.io.
- Self-Guards Apply: MCP tool calls respect the same guards/pauses as the UI.
Implementation Patterns
- At startup / refresh: Load vendored X resources; copy to app data in production if needed.
- Backend client: Validate/build queries using skill.md knowledge; prefix prompts with current capabilities excerpt.
- MCP Server: Tools like
search_x_opportunities,analyze_and_decide,generate_prep_with_guards,promote_with_preview. - UI: Command palette maps 1:1 to MCP tools.
- Prompt library: Central file combining X skill + CV packet + app state.
- Testing: bdd-strategizer for guard scenarios (429, low rate, pause).
Guardrails
- Never assume X API behavior not in current skill.md/llms.
- Writes (posts, DMs): always guard + user pause.
- Rate limits: surface from headers; backoff in reactor.
- Auth: secure OS keyring or encrypted store — never hardcode tokens.
Related
finder-reactor, tauri-agentic, ai-optimization, fusion-sage.
Official: https://docs.x.com/tools/ai
Example provenance: collab-finder.