open-specs-and-standards/profiles

Path
profiles/index.md

Profiles

  • 12-Factor Agents - Nothing to install — thirteen essays whose answer to “who owns the prompts, the context, the state, the control flow?” is always you.
  • Agent2Agent (A2A) Protocol - The load-bearing commitment isn’t the JSON-RPC — it’s opacity. An A2A agent publishes skills, never its prompts, memory, or tools.
  • AGENTS.md - The entire specification is one precedence rule: the closest AGENTS.md to the edited file wins. No schema, no validator.
  • Frictionless Specs - This one specs datasets: every RFC 2119 “MUST” in the prose maps onto a constraint in a published JSON-Schema profile.
  • GSD (Get Shit Done) - GSD’s wager is that the limiting factor is context rot, not spec rigor — so it ships no spec grammar and resets the window per task.
  • llms.txt - The only behavioral semantic in the whole format is an H2 named ## Optional — links there may be dropped when context is tight.
  • MCP-API - However many APIs a user registers, the model only ever sees two tools: ListAvailableApis and CallApi.
  • Model Context Protocol (MCP) - The three client primitives — Sampling, Roots, Elicitation — let a server use the host’s model without ever getting the user’s key.
  • OpenSpec - An LLM should never re-emit a whole spec to change one line, so changes ship as ADDED / MODIFIED / REMOVED deltas.
  • OpenUI - JSON spends ~30% of its bytes on punctuation an LLM has no reason to emit; the same seven UIs cost 47–67% fewer tokens in OpenUI Lang.
  • Spec Kit - No plan gets past the Simplicity, Anti-Abstraction, and Integration-First gates without a written, paper-trailed exception.
  • Superpowers - A SessionStart hook injects the bootstrap skill as <EXTREMELY_IMPORTANT> before the agent has written its first word.
  • Symphony - OpenAI shipped the spec, not the product: 2169 lines of RFC 2119 with sections deliberately made redundant for coding agents.