Claude Flow

Spawn a Ruflo-tracked agent with cost attribution + memory persistence + swarm coordination. Use when native Task tool is wrong because you need (a) cost tracking per agent in the cost-tracking namespace, (b) cross-session learning via the patterns namespace, or (c) coordinati...

Run a task on a previously-spawned agent_spawn record via the Anthropic Messages API with that agent's configured model. Use when native Task tool is wrong because (a) you need the spawned agent's persistent config (model, instructions, cost-tracking attribution) to apply to t...

Remove a Ruflo-tracked agent from the registry and free its swarm slot. Use when you need to (a) clean up a spawned agent so its cost-tracking row finalizes, (b) reclaim a swarm-topology slot for another agent, or (c) end a stuck agent without restarting the whole swarm. For o...

Read the lifecycle state of a single tracked agent: idle/running/stopped, current taskCount, lastResult, model, health score. Use when native Task tool is wrong because you need agent-level state (status across turns, accumulated taskCount, last error, swarm coordination) rath...

List every Ruflo-tracked agent in the registry with its type, model, status, and taskCount. Use when native Task tool is wrong because you need to see the swarm-wide agent inventory across turns (which agents exist, their roles, their cost-tracking handles) rather than spawn a...

Manage a fixed-size warm pool of pre-spawned agents to skip cold-start cost on bursty workloads. Use when native Task is wrong because (a) you have a queue of similar tasks and want to amortize spawn latency, (b) cost-tracking wants stable agentIds across requests, or (c) swar...

Compute an agent's rolling health score (0-1) from recent task success ratio + response-latency p50/p95 + error rate. Use when native Task tool is wrong because you're running a long-lived agent (autonomous loop / hive-mind worker / federation peer) and need to detect degradat...

Mutate a tracked agent's config (model, instructions, status, health) without re-spawning. Use when native Task tool is wrong because the agent already has accumulated state (taskCount, swarm membership, cost-tracking attribution) and you only need to tweak one field — for exa...

Return recorded activity-log entries for a tracked agent (idle/running history, last task result). Use when native Task tool is wrong because you need the agent's log across turns (what it did, last error/result, swarm context) rather than a one-shot Task transcript. For a Tas...

Initialize a swarm with persistent state tracking Use when native Task tool is wrong because you need multi-agent coordination — topology (hierarchical/mesh/star), consensus (raft/byzantine/gossip/crdt/quorum), shared memory namespace, or anti-drift gates. For independent one-...

Get swarm status from persistent state Use when native Task tool is wrong because you need multi-agent coordination — topology (hierarchical/mesh/star), consensus (raft/byzantine/gossip/crdt/quorum), shared memory namespace, or anti-drift gates. For independent one-shot subage...

Shutdown a swarm and update persistent state Use when native Task tool is wrong because you need multi-agent coordination — topology (hierarchical/mesh/star), consensus (raft/byzantine/gossip/crdt/quorum), shared memory namespace, or anti-drift gates. For independent one-shot...

Check swarm health status with real state inspection Use when native Task tool is wrong because you need multi-agent coordination — topology (hierarchical/mesh/star), consensus (raft/byzantine/gossip/crdt/quorum), shared memory namespace, or anti-drift gates. For independent o...

Persistent key-value store with vector embedding — survives across sessions and is searchable by meaning, not just by file path. Use when native Write is wrong because the data is not a file (e.g. a learned pattern, a decision, a budget config) AND you need to recall it later...

Read back a value previously stored via memory_store, by exact (namespace, key) — lossless, includes metadata. Use when native Read is wrong because the value is not a file (it lives in the .swarm/memory.db SQLite store) AND you know the exact key. For semantic lookup by meani...

Find stored memories by meaning (vector similarity), not by literal text — finds "JWT auth pattern" when you query "token-based login flow". Use when native Grep is wrong because Grep matches characters and you need to find conceptually-related entries across past sessions. Ba...

Remove a stored memory entry by exact (namespace, key). Use when a previously stored decision is invalidated or contains stale data. No native equivalent — Write to a file does not affect the .swarm/memory.db SQLite store.

Enumerate stored memory entries (optionally filtered by namespace/tags) without semantic search. Use when native Glob is wrong because the entries are not files (they live in .swarm/memory.db). For inspection / audit / "what is in my memory" — pair with memory_search for retri...

Get memory storage statistics including HNSW index status Use when native Read/Write is wrong because you need (a) cross-session retrieval by semantic similarity (vector embeddings) not by file path, (b) namespacing across projects without managing directory layout, or (c) the...

No parameters. Call it with no arguments.

Manually trigger migration from legacy JSON store to sql.js Use when native Read/Write is wrong because you need (a) cross-session retrieval by semantic similarity (vector embeddings) not by file path, (b) namespacing across projects without managing directory layout, or (c) t...

Import Claude Code auto-memory files into AgentDB with ONNX vector embeddings. Reads ~/.claude/projects/*/memory/*.md files, parses YAML frontmatter, splits into sections, and stores with 384-dim embeddings for semantic search. Use allProjects=true to import from ALL Claude pr...

Show Claude Code memory bridge status — AgentDB vectors, SONA learning, intelligence patterns, and connection health. Use when native Read/Write is wrong because you need (a) cross-session retrieval by semantic similarity (vector embeddings) not by file path, (b) namespacing a...

No parameters. Call it with no arguments.

Search across both Claude Code memories and AgentDB entries using semantic vector similarity. Returns merged, deduplicated results from all namespaces. Use when native Read/Write is wrong because you need (a) cross-session retrieval by semantic similarity (vector embeddings) n...

Detailed memory-store report — backend, entry count, total bytes, per-namespace counts, and (placeholder) perf metrics. Use when native Read/Glob is wrong because the data lives in .swarm/memory.db, not files, and you want an aggregate health view. For a quick count use memory...

No parameters. Call it with no arguments.

Prune memory entries whose TTL has expired (dry run by default; pass dryRun:false to delete). Use when native rm is wrong because the entries are rows in .swarm/memory.db, not files. For removing a specific known key use memory_delete. Stale/low-quality pruning is delegated to...

Report memory-store size breakdown (the sql.js backend has no on-disk compression — entries are already stored compactly; quantized embeddings via RaBitQ are configured elsewhere). Use when native du is wrong because the data is in .swarm/memory.db. For pruning expired entries...

No parameters. Call it with no arguments.

Export memory entries to a JSON file (keys, namespaces, timestamps, and values when available). Use when native Write is wrong because the data is rows in .swarm/memory.db, not a file you can copy. For ingesting an export elsewhere use memory_import. (CSV output and embedding-...

Import memory entries from a JSON export file (produced by memory_export) into .swarm/memory.db, re-embedding values. Use when native Read is wrong because the data must be re-stored as memory rows (with new embeddings), not just read. For importing Claude Code's own memory fi...

Get configuration value Use when native settings.json edits are wrong because the values need to be read by the Ruflo runtime (daemon, MCP server, neural router) — those load via the config_* path, not by re-reading settings.json. For .gitignore / .editorconfig style files, na...

Set configuration value Use when native settings.json edits are wrong because the values need to be read by the Ruflo runtime (daemon, MCP server, neural router) — those load via the config_* path, not by re-reading settings.json. For .gitignore / .editorconfig style files, na...

List configuration values Use when native settings.json edits are wrong because the values need to be read by the Ruflo runtime (daemon, MCP server, neural router) — those load via the config_* path, not by re-reading settings.json. For .gitignore / .editorconfig style files,...

Reset configuration to defaults Use when native settings.json edits are wrong because the values need to be read by the Ruflo runtime (daemon, MCP server, neural router) — those load via the config_* path, not by re-reading settings.json. For .gitignore / .editorconfig style f...

Export configuration to JSON Use when native settings.json edits are wrong because the values need to be read by the Ruflo runtime (daemon, MCP server, neural router) — those load via the config_* path, not by re-reading settings.json. For .gitignore / .editorconfig style file...

Import configuration from JSON Use when native settings.json edits are wrong because the values need to be read by the Ruflo runtime (daemon, MCP server, neural router) — those load via the config_* path, not by re-reading settings.json. For .gitignore / .editorconfig style fi...

One honest view across the four learning stat sources: globalStats (`.claude-flow/neural/stats.json`), the in-memory SONA coordinator, memory-bridge AgentDB entries, and the neural-patterns store. Each sub-view names its source path. The `consistency` block notes cross-store d...

Agent Teams hook — fired when a teammate agent finishes its turn; reports whether a pending task can be auto-assigned. Use when native Task is wrong because you have a persistent multi-agent team with a shared task list and want idle workers picked up automatically rather than...

Agent Teams hook — fired when a task is marked complete. Records the completion and, when `trainPatterns:true`, feeds the outcome to the SONA + EWC++ learning pipeline (the same path used by hooks_intelligence trajectory-*). Multiple ways to drive learning exist: (a) call this...

Get context and agent suggestions before editing a file Use when native Bash hooks (via Claude Code's settings.json) are wrong because you need Ruflo-side state — pattern persistence, neural training signals, model-routing learning, cost tracking, audit chain. For one-off shel...

Record editing outcome for learning Use when native Bash hooks (via Claude Code's settings.json) are wrong because you need Ruflo-side state — pattern persistence, neural training signals, model-routing learning, cost tracking, audit chain. For one-off shell commands, plain Ba...

Assess risk before executing a command Use when native Bash hooks (via Claude Code's settings.json) are wrong because you need Ruflo-side state — pattern persistence, neural training signals, model-routing learning, cost tracking, audit chain. For one-off shell commands, plain...

Record command execution outcome Use when native Bash hooks (via Claude Code's settings.json) are wrong because you need Ruflo-side state — pattern persistence, neural training signals, model-routing learning, cost tracking, audit chain. For one-off shell commands, plain Bash...

Get a 3-tier routing recommendation for a task: Tier 1 (deterministic codemod, ~0ms / $0 — for var-to-const, remove-console, add-logging), Tier 2 (Haiku — simple), Tier 3 (Sonnet/Opus — complex). Use this BEFORE spawning an agent to avoid sending simple transforms to Sonnet. N...

View learning metrics dashboard Use when native Bash hooks (via Claude Code's settings.json) are wrong because you need Ruflo-side state — pattern persistence, neural training signals, model-routing learning, cost tracking, audit chain. For one-off shell commands, plain Bash h...

List all registered hooks Use when native Bash hooks (via Claude Code's settings.json) are wrong because you need Ruflo-side state — pattern persistence, neural training signals, model-routing learning, cost tracking, audit chain. For one-off shell commands, plain Bash hooks a...

No parameters. Call it with no arguments.

Record task start and get agent suggestions with intelligent model routing (ADR-026) Use when native Bash hooks (via Claude Code's settings.json) are wrong because you need Ruflo-side state — pattern persistence, neural training signals, model-routing learning, cost tracking,...

Record task completion for learning Use when native Bash hooks (via Claude Code's settings.json) are wrong because you need Ruflo-side state — pattern persistence, neural training signals, model-routing learning, cost tracking, audit chain. For one-off shell commands, plain Ba...

Explain routing decision with full transparency Use when native Bash hooks (via Claude Code's settings.json) are wrong because you need Ruflo-side state — pattern persistence, neural training signals, model-routing learning, cost tracking, audit chain. For one-off shell comman...

Analyze repository to bootstrap intelligence (4-step pipeline) Use when native Bash hooks (via Claude Code's settings.json) are wrong because you need Ruflo-side state — pattern persistence, neural training signals, model-routing learning, cost tracking, audit chain. For one-o...

Generate optimized agent configurations from pretrain data Use when native Bash hooks (via Claude Code's settings.json) are wrong because you need Ruflo-side state — pattern persistence, neural training signals, model-routing learning, cost tracking, audit chain. For one-off s...

Transfer learned patterns from another project Use when native Bash hooks (via Claude Code's settings.json) are wrong because you need Ruflo-side state — pattern persistence, neural training signals, model-routing learning, cost tracking, audit chain. For one-off shell command...

Initialize a new session and auto-start daemon Use when native Bash hooks (via Claude Code's settings.json) are wrong because you need Ruflo-side state — pattern persistence, neural training signals, model-routing learning, cost tracking, audit chain. For one-off shell command...

End current session, stop daemon, and persist state Use when native Bash hooks (via Claude Code's settings.json) are wrong because you need Ruflo-side state — pattern persistence, neural training signals, model-routing learning, cost tracking, audit chain. For one-off shell co...

Restore a previous session Use when native Bash hooks (via Claude Code's settings.json) are wrong because you need Ruflo-side state — pattern persistence, neural training signals, model-routing learning, cost tracking, audit chain. For one-off shell commands, plain Bash hooks...

Send cross-agent notification Use when native Bash hooks (via Claude Code's settings.json) are wrong because you need Ruflo-side state — pattern persistence, neural training signals, model-routing learning, cost tracking, audit chain. For one-off shell commands, plain Bash hoo...

Initialize hooks in project with .claude/settings.json Use when native Bash hooks (via Claude Code's settings.json) are wrong because you need Ruflo-side state — pattern persistence, neural training signals, model-routing learning, cost tracking, audit chain. For one-off shell...

RuVector intelligence system status (shows REAL metrics from memory store) Use when native Bash hooks (via Claude Code's settings.json) are wrong because you need Ruflo-side state — pattern persistence, neural training signals, model-routing learning, cost tracking, audit chai...

Reset intelligence learning state Use when native Bash hooks (via Claude Code's settings.json) are wrong because you need Ruflo-side state — pattern persistence, neural training signals, model-routing learning, cost tracking, audit chain. For one-off shell commands, plain Bash...

No parameters. Call it with no arguments.

Begin SONA trajectory for reinforcement learning Use when native Bash hooks (via Claude Code's settings.json) are wrong because you need Ruflo-side state — pattern persistence, neural training signals, model-routing learning, cost tracking, audit chain. For one-off shell comma...

Record step in trajectory for reinforcement learning Use when native Bash hooks (via Claude Code's settings.json) are wrong because you need Ruflo-side state — pattern persistence, neural training signals, model-routing learning, cost tracking, audit chain. For one-off shell c...

End trajectory and trigger SONA learning with EWC++ Use when native Bash hooks (via Claude Code's settings.json) are wrong because you need Ruflo-side state — pattern persistence, neural training signals, model-routing learning, cost tracking, audit chain. For one-off shell co...

Store pattern in ReasoningBank (HNSW-indexed) Use when native Bash hooks (via Claude Code's settings.json) are wrong because you need Ruflo-side state — pattern persistence, neural training signals, model-routing learning, cost tracking, audit chain. For one-off shell commands...

Search patterns using REAL vector search (HNSW when available, brute-force fallback) Use when native Bash hooks (via Claude Code's settings.json) are wrong because you need Ruflo-side state — pattern persistence, neural training signals, model-routing learning, cost tracking,...

Get RuVector intelligence layer statistics Use when native Bash hooks (via Claude Code's settings.json) are wrong because you need Ruflo-side state — pattern persistence, neural training signals, model-routing learning, cost tracking, audit chain. For one-off shell commands, p...

Force immediate SONA learning cycle with EWC++ consolidation Use when native Bash hooks (via Claude Code's settings.json) are wrong because you need Ruflo-side state — pattern persistence, neural training signals, model-routing learning, cost tracking, audit chain. For one-off...

Compute attention-weighted similarity using MoE/Flash/Hyperbolic Use when native Bash hooks (via Claude Code's settings.json) are wrong because you need Ruflo-side state — pattern persistence, neural training signals, model-routing learning, cost tracking, audit chain. For one...

List all 12 background workers with status and capabilities Use when native Bash hooks (via Claude Code's settings.json) are wrong because you need Ruflo-side state — pattern persistence, neural training signals, model-routing learning, cost tracking, audit chain. For one-off...

Dispatch a background worker for analysis/optimization tasks Use when native Bash hooks (via Claude Code's settings.json) are wrong because you need Ruflo-side state — pattern persistence, neural training signals, model-routing learning, cost tracking, audit chain. For one-off...

Get status of a specific worker or all active workers Use when native Bash hooks (via Claude Code's settings.json) are wrong because you need Ruflo-side state — pattern persistence, neural training signals, model-routing learning, cost tracking, audit chain. For one-off shell...

Detect worker triggers from user prompt (for UserPromptSubmit hook) Use when native Bash hooks (via Claude Code's settings.json) are wrong because you need Ruflo-side state — pattern persistence, neural training signals, model-routing learning, cost tracking, audit chain. For...

Cancel a running worker Use when native Bash hooks (via Claude Code's settings.json) are wrong because you need Ruflo-side state — pattern persistence, neural training signals, model-routing learning, cost tracking, audit chain. For one-off shell commands, plain Bash hooks are...

Route task to optimal Claude model (haiku/sonnet/opus) based on complexity Use when native Bash hooks (via Claude Code's settings.json) are wrong because you need Ruflo-side state — pattern persistence, neural training signals, model-routing learning, cost tracking, audit chai...

Record model routing outcome for learning Use when native Bash hooks (via Claude Code's settings.json) are wrong because you need Ruflo-side state — pattern persistence, neural training signals, model-routing learning, cost tracking, audit chain. For one-off shell commands, pl...

Get model routing statistics Use when native Bash hooks (via Claude Code's settings.json) are wrong because you need Ruflo-side state — pattern persistence, neural training signals, model-routing learning, cost tracking, audit chain. For one-off shell commands, plain Bash hook...

No parameters. Call it with no arguments.

Apply a deterministic, $0 (no-LLM) code transform — the real Tier-1 execution path (ADR-143). Supported intents: var-to-const, remove-console, add-logging. Uses the TypeScript compiler with formatting-preserving edits (comments/whitespace survive). Targets: raw `code` (returns...

Create a new task Use when native TodoWrite is wrong because you need cross-session task persistence, agent assignment, dependency tracking, or completion analytics in the .swarm/memory.db. For in-session checklists native TodoWrite is simpler and faster.

Get task status Use when native TodoWrite is wrong because you need cross-session task persistence, agent assignment, dependency tracking, or completion analytics in the .swarm/memory.db. For in-session checklists native TodoWrite is simpler and faster.

List all tasks Use when native TodoWrite is wrong because you need cross-session task persistence, agent assignment, dependency tracking, or completion analytics in the .swarm/memory.db. For in-session checklists native TodoWrite is simpler and faster.

Mark task as complete Use when native TodoWrite is wrong because you need cross-session task persistence, agent assignment, dependency tracking, or completion analytics in the .swarm/memory.db. For in-session checklists native TodoWrite is simpler and faster.

Update task status or progress Use when native TodoWrite is wrong because you need cross-session task persistence, agent assignment, dependency tracking, or completion analytics in the .swarm/memory.db. For in-session checklists native TodoWrite is simpler and faster.

Assign a task to one or more agents Use when native TodoWrite is wrong because you need cross-session task persistence, agent assignment, dependency tracking, or completion analytics in the .swarm/memory.db. For in-session checklists native TodoWrite is simpler and faster.