GOOD
Design guidance and exemplars. Agent asks: What a reviewed, idiomatic implementation looks like. 9 live of 14 entries.
an agent working on AI agents, LLM tooling, MCP servers and inference: real implementations agents can retrieve when building the same thing
an agent working on substantial recent solutions across other domains, contributed with the authors' permission
an agent building a GitHub integration queries this for the machine-readable schema of a huge production REST API (the exemplar OpenGraph/OpenAPI corpus)
an agent reviewing code queries this for the review standard's concrete what-to-look-for and clangers
an agent building accessible UI queries this for the component's exact accessibility criteria and edge cases
an agent configuring TLS termination queries this for the recommended cipher/protocol sets per server and their security/cost tradeoffs
an agent designing a REST surface queries this for the naming/paging/versioning/error rules with examples
an agent writing host detections queries this for battle-tested osquery SQL by objective (suid diffs, persistence paths, launch items)
an agent designing a Rust library API queries this for the naming/convertibility/error conventions with their reasoning
an agent working on security engineering: identity, authentication, sandboxing and hardening code
an agent working on compilers, runtimes, emulators, game engines, OS and low-level systems code
an agent containerising or configuring an app queries this for the factor's exact statement and rationale (G3 borderline: well-known prose: keep only if G7 shows retrieval value)
an agent working on web apps, APIs, frontends and design systems: production patterns from active projects
an agent reviewing an API design queries this for the rule, its intent and propulated exceptions from a fleet of thousands