Grok FAF

Introspect the effective orchestration policy WITHOUT running the orchestrator. Returns `{ tier, thresholds, source, overrides_applied }` — what aggressiveness tier the next `faf_orchestrate_recommendation` call would use, and whether it came from defaults or a `.faf:orchestration:` override. No drift detection, no signals, no receipt — pure introspection. Read-only.

Create a project.faf — the IANA-registered context file (application/vnd.faf+yaml) that gives Grok persistent project DNA (stack, structure, intent) in one portable file, so an agent reads the whole project cold each session instead of re-discovering it. Writes project.faf to the target directory (created if missing) and refuses to overwrite an existing context file unless `force` is set. Run once at project start, or with `force` to regenerate, then call faf_score to check readiness. Returns a text confirmation with the written file path and the detected project type.

Heavy orchestrator — given current substrate state, returns a structured recommendation about drift: which refresh to call (or `no_action`), why, how severe, and the underlying signals. ADVISORY ONLY — never auto-fires. Composes the full 1.5 substrate (drift detection · contradiction check · repeat-offender · take-a-hint · refresh history). Writes a recommendation receipt on every call (auditable trail, no silent decisions). Read-only WRT substrate state.

Score a project's AI-readiness 0–100% against the fixed 33-slot context model — how much project DNA an agent has before it has to guess. Deterministic: the same .faf always scores the same. Returns the score, tier, and per-slot breakdown.

Sync project.faf into your AI context files (CLAUDE.md, AGENTS.md, .cursorrules, GEMINI.md). Non-destructive: injects a structured .faf block at the top for fast machine reading and preserves your prose below. One source of truth, every tool kept current.

Validate a project.faf's structure and integrity — confirm the context file is well-formed and parses cleanly before an agent grounds on it. The pre-flight trust check: never build on a broken context layer.

Clear the LAZY-RAG cache — drop all cached retrievals so the next rag_query rebuilds from source. Use when the underlying context has changed and you want fresh results instead of cached ones.

Get LAZY-RAG cache statistics - hits, misses, hit rate, cache size

Ask a question with RAG-enhanced context from xAI Collections. Uses LAZY-RAG cache for 100,000x speedup on repeated queries.

Baked-in two-intensity refresh (Cmd+R / Cmd+Shift+R analog). Fires BOTH `refresh_faf` + `refresh_fafm` in one call. `mode: "blend"` (default) = light `.faf` + delta `.fafm` — the everyday re-ground. `mode: "nuke"` = light `.faf` + verbatim `.fafm` — the hard reload for polluted session memory. Intensity matches drift rate per layer.

Re-ground on the live .faf — re-read + re-score the current project DNA, report drift vs your last-known score, and return the fresh context. The explicit re-grounding primitive for long sessions: drift → refresh → re-grounded. Built for Grok, by request.

Reload the latest structured memory (`.fafm`) for one or more souls into the current session. Returns a stamped delta by default (added/updated facts since last refresh or a given timestamp). Use `verbatim: true` to receive the full current `.fafm` content instead. Read-only. Always returns a content hash + timestamp stamp. Complements `recall`, `load_soul`, and `etch` — does not replace them.