moflo 4.8.9 → 4.8.11

package/.claude/guidance/{memory-strategy.md → shipped/memory-strategy.md}

@@ -1,204 +1,204 @@
-# Memory & Semantic Search Strategy
-
-**Purpose:** How memory, embeddings, and semantic search work in moflo. Reference when debugging memory issues, understanding the search pipeline, or configuring memory for a consumer project.
-
----
-
-## Architecture Overview
-
-```
-Source Files (.claude/guidance/, docs/)
-         |
-         v
-index-guidance.mjs (chunking, RAG linking)
-         |
-         v
-.swarm/memory.db (SQLite - entries + metadata)
-         |
-         v
-build-embeddings.mjs (384-dim neural or hash vectors)
-         |
-         v
-Search layer (cosine similarity - MCP, CLI, or script)
-```
-
----
-
-## Key Files
-
-| File | Purpose |
-|------|---------|
-| `.swarm/memory.db` | SQLite database with all entries, embeddings, metadata |
-| `.swarm/code-map-hash.txt` | SHA-256 hash for incremental code map skip |
-| `.claude-flow/neural/patterns.json` | ReasoningBank learned patterns |
-| `bin/build-embeddings.mjs` | Generates 384-dim embeddings |
-| `bin/index-guidance.mjs` | Indexes guidance files with RAG linking |
-| `bin/generate-code-map.mjs` | Generates structural code map (projects, dirs, types, interfaces) |
-
----
-
-## Embedding Strategy
-
-**Primary model:** `Xenova/all-MiniLM-L6-v2` (384-dim, neural — used by `build-embeddings.mjs`)
-**Fallback model:** `domain-aware-hash-v1` (384-dim, hash — used when Transformers.js unavailable)
-
-**Critical rule:** Query embeddings MUST match stored embeddings. Both the search scripts and MCP tools auto-detect the stored model and generate matching query vectors. Cross-model cosine similarity is meaningless.
-
-**Neural embeddings (primary):**
-- Uses `@xenova/transformers` with ONNX WASM runtime
-- True semantic understanding — "soft delete" matches "mark as deleted" without keyword overlap
-- ~3s for 1000 entries, loaded lazily and cached
-
-**Domain-aware hash (fallback):**
-- 12 domain clusters with project-specific terms
-- SimHash-style word encoding + bigram/trigram features
-- Good keyword-level matching, misses semantic paraphrases
-- No external dependencies — always available, <1s for 1000 entries
-
-See `guidance-memory-strategy.md` for full embedding pipeline details.
-
----
-
-## Search Commands
-
-All methods auto-detect the stored embedding model and generate matching query vectors:
-
-**MCP (Preferred):** `mcp__claude-flow__memory_search` — `query: "your query", namespace: "guidance"`
-
-**CLI (Fallback):**
-```bash
-npx flo memory search --query "your query" --namespace guidance
-```
-
-**Search options:**
-
-| Flag | Default | Purpose |
-|------|---------|---------|
-| `--namespace` | all | Filter to specific namespace |
-| `--limit` | 5 | Number of results |
-| `--threshold` | 0.3 | Minimum similarity score |
-| `--json` | false | Output as JSON |
-
-### Code Map Search (for codebase navigation)
-
-When you need to find where a type, service, entity, or component lives — search `code-map` BEFORE using Glob/Grep:
-
-**MCP:** `mcp__claude-flow__memory_search` — `query: "payment service", namespace: "code-map"`
-
-**What code-map contains:**
-
-| Chunk prefix | What it answers |
-|--------------|-----------------|
-| `project:` | "What's in the api project?" |
-| `dir:` | "What types are in the entities directory?" |
-| `iface-map:` | "What implements IPaymentService?" |
-| `type-index:` | "Where is Service defined?" |
-
-**Regenerate:**
-```bash
-npx flo-codemap          # Incremental (skips if unchanged)
-npx flo-codemap --force  # Full rebuild
-```
-
----
-
-## Database Schema
-
-```sql
-memory_entries (
-  id TEXT PRIMARY KEY,
-  key TEXT NOT NULL,           -- e.g., "chunk-guidance-core-0"
-  namespace TEXT,              -- "guidance", "patterns", "default"
-  content TEXT,                -- Full text content
-  embedding TEXT,              -- JSON array of 384 floats
-  embedding_model TEXT,        -- "Xenova/all-MiniLM-L6-v2" or "domain-aware-hash-v1"
-  embedding_dimensions INTEGER,-- 384
-  metadata TEXT,               -- JSON: parentDoc, chunkTitle, prevChunk, nextChunk, siblings
-  tags TEXT,                   -- JSON array
-  status TEXT,                 -- "active"
-  created_at INTEGER,
-  updated_at INTEGER
-)
-```
-
----
-
-## RAG Linking (metadata fields)
-
-Each chunk includes navigation metadata:
-
-| Field | Purpose |
-|-------|---------|
-| `parentDoc` | Key of full document (e.g., `doc-guidance-core`) |
-| `prevChunk` | Previous chunk key for sequential reading |
-| `nextChunk` | Next chunk key |
-| `siblings` | All chunk keys from same document |
-| `hierarchicalParent` | H2 parent for H3 chunks |
-| `hierarchicalChildren` | H3 children for H2 chunks |
-| `contextBefore` | Overlapping text from previous chunk (20%) |
-| `contextAfter` | Overlapping text from next chunk (20%) |
-
----
-
-## Namespaces
-
-| Namespace | Content | Notes |
-|-----------|---------|-------|
-| `guidance` | Indexed guidance and docs | Largest — includes bundled moflo guidance |
-| `code-map` | Structural codebase index (projects, directories, types, interfaces) | Search BEFORE Glob/Grep for navigation |
-| `patterns` | Learned patterns from sessions | Grows over time |
-| `default` | Misc stored data | Small |
-
----
-
-## Session Start Indexing
-
-On every session start, moflo automatically runs three background indexers:
-
-| Indexer | Command | Namespace | What it does |
-|---------|---------|-----------|--------------|
-| Guidance | `npx flo-index` | `guidance` | Chunks markdown, builds RAG links, generates embeddings |
-| Code Map | `npx flo-codemap` | `code-map` | Scans source for types, interfaces, directories |
-| Learning | `npx flo-learn` | `patterns` | Pattern research on codebase |
-
-These are configured in the `SessionStart` hook in `.claude/settings.json` (set up by `npx flo init`).
-
-Indexing is incremental by default — files whose content hash hasn't changed are skipped. Use `--force` to reindex everything.
-
----
-
-## Troubleshooting
-
-| Symptom | Cause | Fix |
-|---------|-------|-----|
-| Search returns irrelevant results | Query/stored embedding model mismatch | Auto-detected now; verify with `--verbose` flag |
-| Low similarity scores | Query doesn't match domain terms | Include domain keywords in query |
-| "Vector: No" in list | Entry lacks embedding | Run `npx flo-index --force` |
-| Entries not found after adding file | Indexer hasn't run yet | Run `npx flo-index` or restart session |
-| Bundled moflo guidance not indexed | Not installed as dependency | Only indexes when `node_modules/moflo/.claude/guidance/` exists |
-
----
-
-## Verification Commands
-
-```bash
-# Test semantic search
-npx flo memory search --query "database entity pattern" --namespace guidance
-
-# Force reindex all guidance
-npx flo-index --force
-
-# Force rebuild embeddings
-npx flo-index --force
-
-# Check entry count (requires better-sqlite3 or sql.js)
-npx flo memory list --namespace guidance --limit 0
-```
-
----
-
-## See Also
-
-- `.claude/guidance/guidance-memory-strategy.md` - RAG system tuning guide
-- `.claude/guidance/agent-bootstrap.md` - Subagent bootstrap guide
-- `.claude/guidance/moflo.md` - Full CLI/MCP reference
+# Memory & Semantic Search Strategy
+
+**Purpose:** How memory, embeddings, and semantic search work in moflo. Reference when debugging memory issues, understanding the search pipeline, or configuring memory for a consumer project.
+
+---
+
+## Architecture Overview
+
+```
+Source Files (.claude/guidance/, docs/)
+         |
+         v
+index-guidance.mjs (chunking, RAG linking)
+         |
+         v
+.swarm/memory.db (SQLite - entries + metadata)
+         |
+         v
+build-embeddings.mjs (384-dim neural or hash vectors)
+         |
+         v
+Search layer (cosine similarity - MCP, CLI, or script)
+```
+
+---
+
+## Key Files
+
+| File | Purpose |
+|------|---------|
+| `.swarm/memory.db` | SQLite database with all entries, embeddings, metadata |
+| `.swarm/code-map-hash.txt` | SHA-256 hash for incremental code map skip |
+| `.claude-flow/neural/patterns.json` | ReasoningBank learned patterns |
+| `bin/build-embeddings.mjs` | Generates 384-dim embeddings |
+| `bin/index-guidance.mjs` | Indexes guidance files with RAG linking |
+| `bin/generate-code-map.mjs` | Generates structural code map (projects, dirs, types, interfaces) |
+
+---
+
+## Embedding Strategy
+
+**Primary model:** `Xenova/all-MiniLM-L6-v2` (384-dim, neural — used by `build-embeddings.mjs`)
+**Fallback model:** `domain-aware-hash-v1` (384-dim, hash — used when Transformers.js unavailable)
+
+**Critical rule:** Query embeddings MUST match stored embeddings. Both the search scripts and MCP tools auto-detect the stored model and generate matching query vectors. Cross-model cosine similarity is meaningless.
+
+**Neural embeddings (primary):**
+- Uses `@xenova/transformers` with ONNX WASM runtime
+- True semantic understanding — "soft delete" matches "mark as deleted" without keyword overlap
+- ~3s for 1000 entries, loaded lazily and cached
+
+**Domain-aware hash (fallback):**
+- 12 domain clusters with project-specific terms
+- SimHash-style word encoding + bigram/trigram features
+- Good keyword-level matching, misses semantic paraphrases
+- No external dependencies — always available, <1s for 1000 entries
+
+See `guidance-memory-strategy.md` for full embedding pipeline details.
+
+---
+
+## Search Commands
+
+All methods auto-detect the stored embedding model and generate matching query vectors:
+
+**MCP (Preferred):** `mcp__moflo__memory_search` — `query: "your query", namespace: "guidance"`
+
+**CLI (Fallback):**
+```bash
+npx flo memory search --query "your query" --namespace guidance
+```
+
+**Search options:**
+
+| Flag | Default | Purpose |
+|------|---------|---------|
+| `--namespace` | all | Filter to specific namespace |
+| `--limit` | 5 | Number of results |
+| `--threshold` | 0.3 | Minimum similarity score |
+| `--json` | false | Output as JSON |
+
+### Code Map Search (for codebase navigation)
+
+When you need to find where a type, service, entity, or component lives — search `code-map` BEFORE using Glob/Grep:
+
+**MCP:** `mcp__moflo__memory_search` — `query: "payment service", namespace: "code-map"`
+
+**What code-map contains:**
+
+| Chunk prefix | What it answers |
+|--------------|-----------------|
+| `project:` | "What's in the api project?" |
+| `dir:` | "What types are in the entities directory?" |
+| `iface-map:` | "What implements IPaymentService?" |
+| `type-index:` | "Where is Service defined?" |
+
+**Regenerate:**
+```bash
+npx flo-codemap          # Incremental (skips if unchanged)
+npx flo-codemap --force  # Full rebuild
+```
+
+---
+
+## Database Schema
+
+```sql
+memory_entries (
+  id TEXT PRIMARY KEY,
+  key TEXT NOT NULL,           -- e.g., "chunk-guidance-core-0"
+  namespace TEXT,              -- "guidance", "patterns", "default"
+  content TEXT,                -- Full text content
+  embedding TEXT,              -- JSON array of 384 floats
+  embedding_model TEXT,        -- "Xenova/all-MiniLM-L6-v2" or "domain-aware-hash-v1"
+  embedding_dimensions INTEGER,-- 384
+  metadata TEXT,               -- JSON: parentDoc, chunkTitle, prevChunk, nextChunk, siblings
+  tags TEXT,                   -- JSON array
+  status TEXT,                 -- "active"
+  created_at INTEGER,
+  updated_at INTEGER
+)
+```
+
+---
+
+## RAG Linking (metadata fields)
+
+Each chunk includes navigation metadata:
+
+| Field | Purpose |
+|-------|---------|
+| `parentDoc` | Key of full document (e.g., `doc-guidance-core`) |
+| `prevChunk` | Previous chunk key for sequential reading |
+| `nextChunk` | Next chunk key |
+| `siblings` | All chunk keys from same document |
+| `hierarchicalParent` | H2 parent for H3 chunks |
+| `hierarchicalChildren` | H3 children for H2 chunks |
+| `contextBefore` | Overlapping text from previous chunk (20%) |
+| `contextAfter` | Overlapping text from next chunk (20%) |
+
+---
+
+## Namespaces
+
+| Namespace | Content | Notes |
+|-----------|---------|-------|
+| `guidance` | Indexed guidance and docs | Largest — includes bundled moflo guidance |
+| `code-map` | Structural codebase index (projects, directories, types, interfaces) | Search BEFORE Glob/Grep for navigation |
+| `patterns` | Learned patterns from sessions | Grows over time |
+| `default` | Misc stored data | Small |
+
+---
+
+## Session Start Indexing
+
+On every session start, moflo automatically runs three background indexers:
+
+| Indexer | Command | Namespace | What it does |
+|---------|---------|-----------|--------------|
+| Guidance | `npx flo-index` | `guidance` | Chunks markdown, builds RAG links, generates embeddings |
+| Code Map | `npx flo-codemap` | `code-map` | Scans source for types, interfaces, directories |
+| Learning | `npx flo-learn` | `patterns` | Pattern research on codebase |
+
+These are configured in the `SessionStart` hook in `.claude/settings.json` (set up by `npx flo init`).
+
+Indexing is incremental by default — files whose content hash hasn't changed are skipped. Use `--force` to reindex everything.
+
+---
+
+## Troubleshooting
+
+| Symptom | Cause | Fix |
+|---------|-------|-----|
+| Search returns irrelevant results | Query/stored embedding model mismatch | Auto-detected now; verify with `--verbose` flag |
+| Low similarity scores | Query doesn't match domain terms | Include domain keywords in query |
+| "Vector: No" in list | Entry lacks embedding | Run `npx flo-index --force` |
+| Entries not found after adding file | Indexer hasn't run yet | Run `npx flo-index` or restart session |
+| Bundled moflo guidance not indexed | Not installed as dependency | Only indexes when `node_modules/moflo/.claude/guidance/` exists |
+
+---
+
+## Verification Commands
+
+```bash
+# Test semantic search
+npx flo memory search --query "database entity pattern" --namespace guidance
+
+# Force reindex all guidance
+npx flo-index --force
+
+# Force rebuild embeddings
+npx flo-index --force
+
+# Check entry count (requires better-sqlite3 or sql.js)
+npx flo memory list --namespace guidance --limit 0
+```
+
+---
+
+## See Also
+
+- `.claude/guidance/guidance-memory-strategy.md` - RAG system tuning guide
+- `.claude/guidance/agent-bootstrap.md` - Subagent bootstrap guide
+- `.claude/guidance/moflo.md` - Full CLI/MCP reference

package/.claude/guidance/{moflo.md → shipped/moflo.md}

@@ -2,7 +2,7 @@
 
 **Purpose:** Complete CLI and MCP reference for moflo — hooks, memory, agents, swarm, neural, and doctor commands. Read when using moflo features or debugging agent coordination.
 
-**MCP-First Policy:** Always prefer MCP tools (`mcp__claude-flow__*`) over CLI commands. Use `ToolSearch` to load them, then call directly. CLI is fallback only.
+**MCP-First Policy:** Always prefer MCP tools (`mcp__moflo__*`) over CLI commands. Use `ToolSearch` to load them, then call directly. CLI is fallback only.
 
 ---
 
@@ -43,6 +43,20 @@ When a Claude Code session starts, moflo automatically runs three background ind
 
 These run in background and are incremental (unchanged files are skipped). Controlled by `auto_index` in `moflo.yaml`.
 
+### Helper Script Auto-Sync
+
+On version change, `session-start-launcher.mjs` copies helper scripts from the installed moflo package to the consumer project's `.claude/helpers/` and `.claude/scripts/` directories. This ensures hooks always run the latest version.
+
+**Rule: static files, not dynamic generation.** If a helper script has no dynamic content (no per-project interpolation), it must be shipped as a pre-built static file in `bin/` and synced via the session-start file lists. Do not generate static content dynamically at runtime — it adds fragile moving parts (background `init --upgrade`, race conditions with session-start exit) and causes stale scripts when the sync list is incomplete.
+
+| Source | Target | Files |
+|--------|--------|-------|
+| `bin/` | `.claude/scripts/` | `hooks.mjs`, `session-start-launcher.mjs`, `index-guidance.mjs`, `build-embeddings.mjs`, `generate-code-map.mjs`, `semantic-search.mjs` |
+| `bin/` | `.claude/helpers/` | `gate.cjs`, `gate-hook.mjs`, `prompt-hook.mjs`, `hook-handler.cjs` |
+| `src/@claude-flow/cli/.claude/helpers/` | `.claude/helpers/` | `auto-memory-hook.mjs`, `statusline.cjs`, `pre-commit`, `post-commit` |
+
+When adding a new helper script: generate it once, save it to `bin/`, and add it to the appropriate list in `session-start-launcher.mjs`.
+
 ### Bundled Guidance
 
 Moflo ships its own guidance files (in `.claude/guidance/` within the package). When installed as a dependency, these are **automatically indexed** alongside the consumer project's guidance under the `guidance` namespace. This means agents in your project can search for moflo system docs (swarm patterns, memory commands, etc.) without any extra setup.
@@ -79,7 +93,7 @@ MCP tools are the preferred way for Claude to interact with moflo. `flo init` cr
 ```json
 {
   "mcpServers": {
-    "claude-flow": {
+    "moflo": {
       "command": "node",
       "args": ["node_modules/moflo/src/@claude-flow/cli/bin/cli.js", "mcp", "start"]
     }
@@ -87,7 +101,7 @@ MCP tools are the preferred way for Claude to interact with moflo. `flo init` cr
 }
 ```
 
-This gives Claude access to 200+ MCP tools (`mcp__claude-flow__memory_*`, `mcp__claude-flow__hooks_*`, `mcp__claude-flow__swarm_*`, etc.) without any global installation.
+This gives Claude access to 200+ MCP tools (`mcp__moflo__memory_*`, `mcp__moflo__hooks_*`, `mcp__moflo__swarm_*`, etc.) without any global installation.
 
 ---
 
@@ -143,11 +157,11 @@ This gives Claude access to 200+ MCP tools (`mcp__claude-flow__memory_*`, `mcp__
 
 | Task | MCP Tool | CLI Fallback |
 |------|----------|-------------|
-| Search memory | `mcp__claude-flow__memory_search` | `memory search --query "..."` |
-| Spawn agent | `mcp__claude-flow__agent_spawn` | `agent spawn -t coder --name my-coder` |
-| Init swarm | `mcp__claude-flow__swarm_init` | `swarm init --v3-mode` |
-| System health | `mcp__claude-flow__system_health` | `doctor --fix` |
-| Benchmark | `mcp__claude-flow__performance_benchmark` | `performance benchmark --suite all` |
+| Search memory | `mcp__moflo__memory_search` | `memory search --query "..."` |
+| Spawn agent | `mcp__moflo__agent_spawn` | `agent spawn -t coder --name my-coder` |
+| Init swarm | `mcp__moflo__swarm_init` | `swarm init --v3-mode` |
+| System health | `mcp__moflo__system_health` | `doctor --fix` |
+| Benchmark | `mcp__moflo__performance_benchmark` | `performance benchmark --suite all` |
 
 **CLI-only (no MCP equivalent — setup tasks):**
 ```bash
@@ -249,13 +263,13 @@ npx flo daemon start
 
 | Hook | MCP Tool | Key Params |
 |------|----------|------------|
-| Pre-task | `mcp__claude-flow__hooks_pre-task` | `description` |
-| Post-task | `mcp__claude-flow__hooks_post-task` | `taskId`, `success` |
-| Post-edit | `mcp__claude-flow__hooks_post-edit` | `file`, `trainNeural` |
-| Session-start | `mcp__claude-flow__hooks_session-start` | `sessionId` |
-| Session-end | `mcp__claude-flow__hooks_session-end` | `exportMetrics` |
-| Route | `mcp__claude-flow__hooks_route` | `task` |
-| Worker-dispatch | `mcp__claude-flow__hooks_worker-dispatch` | `trigger` |
+| Pre-task | `mcp__moflo__hooks_pre-task` | `description` |
+| Post-task | `mcp__moflo__hooks_post-task` | `taskId`, `success` |
+| Post-edit | `mcp__moflo__hooks_post-edit` | `file`, `trainNeural` |
+| Session-start | `mcp__moflo__hooks_session-start` | `sessionId` |
+| Session-end | `mcp__moflo__hooks_session-end` | `exportMetrics` |
+| Route | `mcp__moflo__hooks_route` | `task` |
+| Worker-dispatch | `mcp__moflo__hooks_worker-dispatch` | `trigger` |
 
 ---
 
@@ -291,7 +305,7 @@ npx flo daemon start
 
 ### Before Starting Coding Tasks
 
-**MCP (Preferred):** `mcp__claude-flow__memory_search` — `query: "[task keywords]", namespace: "patterns"`
+**MCP (Preferred):** `mcp__moflo__memory_search` — `query: "[task keywords]", namespace: "patterns"`
 
 **CLI Fallback:**
 ```bash
@@ -302,9 +316,9 @@ npx flo memory search --query '[task keywords]' --namespace patterns
 
 | Step | MCP Tool | Key Params |
 |------|----------|------------|
-| 1. Store pattern | `mcp__claude-flow__memory_store` | `namespace: "patterns", key: "[name]", value: "[what worked]"` |
-| 2. Train neural | `mcp__claude-flow__hooks_post-edit` | `file: "[main-file]", trainNeural: true` |
-| 3. Record completion | `mcp__claude-flow__hooks_post-task` | `taskId: "[id]", success: true, storeResults: true` |
+| 1. Store pattern | `mcp__moflo__memory_store` | `namespace: "patterns", key: "[name]", value: "[what worked]"` |
+| 2. Train neural | `mcp__moflo__hooks_post-edit` | `file: "[main-file]", trainNeural: true` |
+| 3. Record completion | `mcp__moflo__hooks_post-task` | `taskId: "[id]", success: true, storeResults: true` |
 
 ### Continuous Improvement Triggers
 
@@ -337,7 +351,7 @@ npx flo memory search --query '[task keywords]' --namespace patterns
 
 ### Store Data
 
-**MCP:** `mcp__claude-flow__memory_store`
+**MCP:** `mcp__moflo__memory_store`
 - Required: `key`, `value`
 - Optional: `namespace` (default: "default"), `ttl`, `tags`
 
@@ -348,7 +362,7 @@ npx flo memory store --key "pattern-auth" --value "JWT with refresh tokens" --na
 
 ### Search Data (semantic vector search)
 
-**MCP:** `mcp__claude-flow__memory_search`
+**MCP:** `mcp__moflo__memory_search`
 - Required: `query`
 - Optional: `namespace`, `limit`, `threshold`
 
@@ -359,12 +373,12 @@ npx flo memory search --query "authentication patterns" --namespace patterns --l
 
 ### List Entries
 
-**MCP:** `mcp__claude-flow__memory_list`
+**MCP:** `mcp__moflo__memory_list`
 - Optional: `namespace`, `limit`
 
 ### Retrieve Specific Entry
 
-**MCP:** `mcp__claude-flow__memory_retrieve`
+**MCP:** `mcp__moflo__memory_retrieve`
 - Required: `key`
 - Optional: `namespace` (default: "default")
 
@@ -383,11 +397,11 @@ npx flo memory search --query "authentication patterns" --namespace patterns --l
 
 | Operation | MCP Tool |
 |-----------|----------|
-| Swarm init | `mcp__claude-flow__swarm_init` |
-| Agent spawn | `mcp__claude-flow__agent_spawn` |
-| Memory store | `mcp__claude-flow__memory_store` |
-| Memory search | `mcp__claude-flow__memory_search` |
-| Hooks (all) | `mcp__claude-flow__hooks_<hook-name>` |
+| Swarm init | `mcp__moflo__swarm_init` |
+| Agent spawn | `mcp__moflo__agent_spawn` |
+| Memory store | `mcp__moflo__memory_store` |
+| Memory search | `mcp__moflo__memory_search` |
+| Hooks (all) | `mcp__moflo__hooks_<hook-name>` |
 
 ### CLI Commands (Fallback Only):
 
@@ -402,7 +416,7 @@ npx flo <command> [options]
 
 ## Doctor Health Checks
 
-**MCP:** `mcp__claude-flow__system_health` | **CLI:** `npx flo doctor`
+**MCP:** `mcp__moflo__system_health` | **CLI:** `npx flo doctor`
 
 Checks: Node version (20+), Git, config validity, daemon status, memory database, API keys, MCP servers, disk space, TypeScript.
 
@@ -436,7 +450,7 @@ Configure `.mcp.json` in the project root:
 ```json
 {
   "mcpServers": {
-    "claude-flow": {
+    "moflo": {
       "command": "node",
       "args": ["node_modules/moflo/src/@claude-flow/cli/bin/cli.js", "mcp", "start"]
     }
@@ -447,7 +461,7 @@ Configure `.mcp.json` in the project root:
 ### Alternative: Global MCP Registration
 
 ```bash
-claude mcp add claude-flow -- npx @claude-flow/cli@alpha
+claude mcp add moflo -- npx @claude-flow/cli@alpha
 npx flo daemon start
 npx flo doctor --fix
 ```