Grok FAF

🖼️ Render project.faf → project.html (faf-cli's real scorer + renderer — the same context your AI reads)

🧬 Show Birth DNA and evolution tracking

🏥 Comprehensive health check for .faf and environment

Interactive editor with validation

Check if file or directory exists

Interactive help system

🐱 TURBO-CAT format discovery (153 validated formats)

Friday features — Chrome Extension detection, fuzzy matching

Description is built at runtime.

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.

FAF MCP usage guide for Claude Desktop - Projects convention, path resolution, and UX patterns

A-Z reference catalog of your project

Initialize FAF with intelligent project detection - Championship grade

🇬🇧 British version of init - same championship, more bruv!

🏆 Install faf-expert skill to Claude Code - Automatic installation of world-class FAF expertise

List directory contents

📜 Show DNA evolution history and changes

Phase III — structured portable memory. Query the durable .fafm model (decisions/invariants/conventions/WHY) by type/tag/priority/text instead of scrolling a flat GROK.md. Omit all filters for a structured summary (counts by type/priority + tag vocabulary + index). NOTE: .fafm is NOT scored — this SELECTS and returns facts (provenance preserved), it never grades them. Read-only; complements refresh_fafm/recall.

🔄 Migrate .faf to project.faf (format v2.5.0)

Create directories

Move or rename files

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.

⚡ Quick .faf creation - one-liner for instant context. Creates in ~/Projects/ (or ~/projects/ if exists).

Read any file

🚑 Recover .faf from backups or DNA history

Championship scorecard with actionable insights. CRITICAL: Content between [DISPLAY:REQUIRED] tags MUST be displayed directly to user as formatted markdown. Do NOT summarize. Includes Quick Actions for immediate next steps.

Search filesystem for files by name (TURBO-CAT powered). Solves the "dropped file path" problem - find where a file lives.

Phase III — structure-aware retrieval. Returns an EXACT, WHOLE .faf section by dotted path (e.g. "stack", "stack.backend", "human_context"), structure and relationships preserved — the deterministic complement to Collections' blind ~1024-token chunking (which flattens a .faf). Omit "section" to list every available path. No LLM, no Collections call: parse → resolve path → return the whole subtree as YAML.

Secure sharing with auto-sanitization

🟠 FORCE DISPLAY raw FAF output - Shows EXACTLY what FAF generates!

🎸 List Claude Code skills from .faf file - See which skills are configured for this project

STACKTISTICS technology discovery

Comprehensive project status with Championship Medal System

Synchronize .faf with CLAUDE.md

Gamified improvement tracking system

Trust validation with 4 modes

Trust with confidence mode - steady state

Trust garage mode - under the hood

Trust panic mode - emergency validation

Trust validated mode - championship seal

🔄 Update .faf file with latest project information

Validate .faf file structure and completeness

Verify with Claude, ChatGPT, Gemini

Show FAF version with MK2 engine and TURBO-CAT status

Quick explanation of .faf format

Write any file

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. Reads your files and writes a refresh receipt (.fafm-refresh-receipts.json) to the project folder. Always returns a content hash + timestamp stamp. Complements `recall`, `load_soul`, and `etch` — does not replace them.