Dev-Guides Navigator

Route to the correct online guide and enforce guide application.

Six modes

The navigator exposes six independent routing modes over the published catalogs:

• Guide search (llms.txt) — atomic, mechanics-level decision guides. The original flow. See Core Workflow below.
• Recipe search (agentic-recipes.txt) — goal-oriented, prescriptive capability deliveries that sequence existing guides/plays end-to-end and carry a verifier. See Recipe Search below.
• Process-recipe lookup (process-recipes.txt) — resolved by ai-dev-assistant at lifecycle phase boundaries, keyed by (phase, framework). See Process-Recipe Lookup below. Never matched during free task routing.
• Identify (llms.txt, agentic-recipes.txt, tooling-recipes.txt) — report what covers a topic, and open nothing. See Identify below.
• Playbook lookup (llms.txt, then <topic>/plays.json): resolved by ai-dev-assistant at research, keyed by a playbook set id. See Playbook Lookup below. Never matched during free task routing.
• Tooling lookup (tooling-recipes.txt): resolved by aida's design stage, keyed by name. See Tooling Lookup below. Never matched during free task routing.

The six are two groups. Guide search and recipe search resolve a body and apply it in place, because applying a guide means reading it. Process-recipe lookup, identify, playbook lookup and tooling lookup return a structured report and never stream a body. A caller that must name what exists without paying to read it wants the second group.

The navigator does not hardcode an order. The caller owns ordering — typically recipe-search first (is there a prescriptive end-to-end recipe for this capability?), then guide-search (fall back to raw mechanics). Recipe search never fabricates a recipe: a miss cleanly defers to guide search. Process-recipe lookup is invoked only by ai-dev-assistant, not during free task routing.