Files
ruvnet__ruflo/plugins/README.md
rUv ef73a1616f feat(ruflo-agent): rename ruflo-wasm → ruflo-agent + Claude Managed Agents (cloud) runtime — ADR-115 (proposed→accepted, implemented) (#1929)
* docs(adr): ADR-115 — Claude Managed Agents as a cloud backend for rvagent (explored + validated)

Records the proposal to add `runtime: "managed"` to ruflo's rvagent
interface (ruflo-wasm / @ruvector/rvagent-wasm / wasm_agent_* MCP tools),
backed by Anthropic's Claude Managed Agents API (beta), as a second backend
alongside the local WASM sandbox — mirroring the ConsensusTransport
LocalTransport|FederationTransport pattern (ADR-095 G2 / ADR-104). The
agent/environment/session/events model maps ~1:1 to wasm_agent_create/
prompt/files/terminate + the gallery.

Validated live against api.anthropic.com/v1 with the org's Anthropic key
(GCP claude-flow/anthropic-api-key): created an agent + environment + session,
sent a bash task, observed the full event log (status_running → user.message
→ tool_use(bash) → tool_result → agent.message("Done.") → status_idle,
stop_reason end_turn), cleaned up. ~7s for a trivial Haiku task.

High-value combos noted: ruflo's own MCP server as a Managed Agent tool
source (cloud-hosted ruflo, zero local infra); Managed Agent session as a
third task_assign executor (closes #1916 items 3/4); long-running/async work;
skills + define-outcomes parity. Constraints: opt-in/off-by-default, needs
ANTHROPIC_API_KEY + beta access, plugin-level @anthropic-ai/sdk dep,
cost-tracking + orphaned-session GC, beta churn, branding.

Status: proposed. Registered in AgentDB (adr-ADR-115) + adr-patterns.

Co-Authored-By: RuFlo <ruv@ruv.net>

* refactor(plugins): rename ruflo-wasm → ruflo-agent (agent-runtimes home; ADR-115 prep)

`ruflo-wasm` only covered local WASM-sandboxed agents (rvagent —
@ruvector/rvagent-wasm, the wasm_agent_*/wasm_gallery_* MCP tools). It's
becoming the home for *all* ruflo agent runtimes: the existing local-WASM
backend plus Anthropic's Claude Managed Agents as a cloud backend (ADR-115),
behind one interface — same local-vs-cloud pattern as ConsensusTransport.

- git mv plugins/ruflo-wasm → plugins/ruflo-agent
- plugin.json: name ruflo-wasm → ruflo-agent; description/keywords now span
  both runtimes (rvagent/wasm + managed-agents/anthropic/cloud)
- .claude-plugin/marketplace.json entry renamed
- README / plugins/README / docs/index / cli README / ruflo README /
  discover-plugins SKILL / verification/inventory.json / ADR-115 — refs updated
- wasm_agent_* / wasm_gallery_* MCP tool names are unchanged (they stay; the
  plugin is just renamed). managed_agent_* tools land next per ADR-115.

(Left `ruflo-wasm-mcp` in ruvocal/workerClient.ts alone — unrelated worker MCP name.)

Co-Authored-By: RuFlo <ruv@ruv.net>

* feat(cli): managed_agent_* MCP tools — Claude Managed Agents cloud runtime (ADR-115)

Six new MCP tools wrapping Anthropic's Claude Managed Agents REST API (beta,
`anthropic-beta: managed-agents-2026-04-01`) via plain fetch — no new SDK dep:

  managed_agent_create    agents.create + environments.create + sessions.create   ↔ wasm_agent_create (CLOUD counterpart)
  managed_agent_prompt    events.send(user.message) + poll events until idle       ↔ wasm_agent_prompt
  managed_agent_status    GET /v1/sessions/{id}
  managed_agent_events    GET /v1/sessions/{id}/events  (full transcript)           ↔ wasm_agent_files
  managed_agent_list      GET /v1/sessions
  managed_agent_terminate DELETE /v1/sessions/{id} (+ optionally the env)           ↔ wasm_agent_terminate

Needs ANTHROPIC_API_KEY (or CLAUDE_API_KEY); every tool degrades gracefully
with a structured "use wasm_agent_* for a local no-key runtime" error when the
key is absent — the CLI/MCP server stays up. ADR-112-compliant descriptions
(each says when wasm_agent_* / native is the right call instead). Registered
in mcp-client.ts. Lives conceptually in the `ruflo-agent` plugin (the
`ruflo-wasm`→`ruflo-agent` rename in the prior commit).

Validated live against api.anthropic.com with the org's Anthropic key (GCP
claude-flow/anthropic-api-key) via `ruflo mcp exec -t managed_agent_*`:
create (haiku) → prompt ("echo … > /tmp/r.txt && cat") → got finished:true,
status:idle, stopReason:end_turn, assistantText:"Done.", toolUses:[bash],
13 events → terminate (sessionDeleted+environmentDeleted). No-key path returns
the graceful error. audit-cli-mcp-tools 311 registered/0 dangling;
audit-tool-descriptions 0 no-guidance; cli build clean.

Co-Authored-By: RuFlo <ruv@ruv.net>

* feat(ruflo-agent): wire the managed-agent (cloud) runtime into the plugin + CI smoke

- skills/managed-agent/SKILL.md — drives the cloud runtime: managed_agent_create
  / prompt / status / events / list / terminate, with the WASM-vs-managed
  decision table, the ANTHROPIC_API_KEY prereq + graceful fallback, the
  mcpServers-reachability caveat, and the cost/cleanup discipline (a cloud
  session bills until terminated). Explicit allowed-tools (no wildcard).
- commands/managed-agent.md — quick "list cloud sessions / status / transcript
  / clean up" command (the cloud sibling of /wasm).
- plugin.json — kept rvagent-wasm + ruvllm-wasm keywords (still built on those);
  added managed-agents/anthropic/cloud.
- smoke.sh: step 1 now also asserts name=ruflo-agent + the managed-agents
  keywords; step 10 expects ADR-0001 status `Accepted` (was stale `Proposed`,
  pre-existing red); new step 12 — managed-agent skill+command exist + all 6
  managed_agent_* tools referenced + the skill keeps an explicit allowed-tools
  list + offers the wasm_agent_create fallback. 12 passed / 0 failed.
- .github/workflows/ruflo-agent-smoke.yml — new CI job running smoke.sh on any
  plugins/ruflo-agent/** change (the plugin had no CI gate before).

Validated: `claude --plugin-dir plugins/ruflo-agent` loads the plugin and lists
its skills (managed-agent, wasm-agent, wasm-gallery); plugin.json + all skill
frontmatters parse; smoke.sh 12/0.

Co-Authored-By: RuFlo <ruv@ruv.net>

* docs(adr): ADR-115 → Accepted + Implementation section (managed_agent_* landed)

Status Proposed → Accepted. Added an Implementation (2026-05-12) section:
the ruflo-wasm→ruflo-agent rename, the 6 managed_agent_* MCP tools (plain
fetch, no new SDK dep, graceful no-key degradation, ADR-112 descriptions),
the managed-agent skill+command, the smoke.sh/ruflo-agent-smoke.yml CI guard,
the live e2e validation (create→prompt→terminate against api.anthropic.com
with the GCP anthropic-api-key) and `claude --plugin-dir` validation, and the
called-out follow-ups (runtime:"managed" unification, deployed HTTP ruflo MCP
server for the cloud-hosted-ruflo combo, task_assign/federation dispatch to a
Managed Agent session, cost-tracking + orphaned-session GC, multiagent/outcomes).
Tracking issue: #1931.

Co-Authored-By: RuFlo <ruv@ruv.net>

* test(cli): no-network guard for managed_agent_* tools (ADR-115)

__tests__/managed-agent-tools.test.ts (10 cases): the 6 managed_agent_*
tools are registered; each has an object inputSchema + a ≥80-char,
ADR-112-ish, unique description that names the wasm_agent_*/native fallback;
and — crucially — every handler degrades gracefully with no ANTHROPIC_API_KEY/
CLAUDE_API_KEY: no throw, structured error mentioning the key + the
wasm_agent_create fallback, no network call (so the CLI/MCP server stays up
offline). Plus managed_agent_prompt's missing-sessionId/message validation.

Co-Authored-By: RuFlo <ruv@ruv.net>

* docs(adr): ADR-115 — add the third runtime (Claude Agent SDK) to the picture

ADR-115 adds the *cloud* runtime (Managed Agents); add a section noting the
natural *third* runtime — the Claude Agent SDK (@anthropic-ai/claude-agent-sdk,
"Claude Code as a library": query()/ClaudeSDKClient, hooks, subagents, MCP,
permission modes, sessions, loads .claude/ config + plugins; runs in-process,
full host trust). ruflo-agent → three runtimes behind one model:

  WASM (rvagent)   local sandbox, no host fs/net   untrusted/portable/offline
  SDK  (future)    your process, your filesystem    a real Claude agent loop on the local repo — the in-process `claude -p`
  Managed          Anthropic cloud container        long-running/async, no local infra

The SDK runtime's killer combo: `mcpServers: { ruflo: { command: "npx", args: ["ruflo","mcp","start"] } }` — a *local* stdio MCP server, so the agent gets ruflo's 314 tools with zero deployment (vs Managed Agents needing a reachable URL). Anthropic positions SDK→Managed as prototype→production. Costs: heavy dep (bundles a Claude Code binary), full host trust (no sandbox — least isolated), needs an API key. Implementing it = a follow-up, likely ADR-116 (tracked in #1931).

Co-Authored-By: RuFlo <ruv@ruv.net>

---------

Co-authored-by: Reuven <cohen@ruv-mac-mini.local>
2026-05-12 10:24:03 -04:00

6.9 KiB

Ruflo Plugins

32 Claude Code plugins for agent-powered development workflows. Load with --plugin-dir.

Quick Start

# Load specific plugins
claude --plugin-dir plugins/ruflo-core --plugin-dir plugins/ruflo-swarm

# Load all plugins
claude $(ls -d plugins/ruflo-*/ | sed 's|^|--plugin-dir |' | tr '\n' ' ')

Plugin Catalog

Core & Coordination

Plugin Description
ruflo-core MCP server, status, doctor, coder/researcher/reviewer agents
ruflo-swarm Swarm topologies (hierarchical, mesh), Monitor streaming
ruflo-autopilot Autonomous /loop task completion with prediction
ruflo-loop-workers 12 background workers via /loop or CronCreate
ruflo-workflows Workflow templates, parallel execution, branching

Memory & Intelligence

Plugin Description
ruflo-agentdb AgentDB with HNSW vector search (150x-12,500x faster)
ruflo-rag-memory SOTA RAG — hybrid search, Graph RAG, MMR diversity, memory bridge
ruflo-rvf Portable RVF memory format, session persistence
ruflo-ruvector ruvector — FlashAttention-3, Graph RAG, hybrid search, 103 MCP tools, Brain AGI
ruflo-knowledge-graph Entity extraction, relation mapping, pathfinder traversal
ruflo-intelligence SONA neural patterns, trajectory learning, model routing
ruflo-daa Dynamic Agentic Architecture, cognitive patterns

Architecture & Methodology

Plugin Description
ruflo-adr ADR lifecycle — create, index, supersede, compliance checking
ruflo-ddd DDD scaffolding — bounded contexts, aggregates, domain events
ruflo-sparc SPARC methodology with 5 phases and quality gates

Quality & Security

Plugin Description
ruflo-security-audit CVE scanning, dependency vulnerability checks
ruflo-aidefence Prompt injection detection, PII scanning
ruflo-testgen Test gap detection, TDD London School workflow
ruflo-browser Playwright browser automation and testing

Development Tools

Plugin Description
ruflo-jujutsu Diff analysis, risk scoring, reviewer recommendations
ruflo-docs Doc generation, drift detection, API docs
ruflo-ruvllm Local LLM inference, MicroLoRA, chat formatting
ruflo-agent WASM agent sandboxing and gallery
ruflo-plugin-creator Scaffold and validate new plugins
ruflo-migrations Database schema migration management
ruflo-observability Structured logging, tracing, metrics correlation
ruflo-cost-tracker Token usage tracking, budget alerts, cost optimization

Domain-Specific

Plugin Description
ruflo-goals GOAP planning, deep research, horizon tracking
ruflo-federation Zero-trust cross-installation agent federation
ruflo-iot-cognitum Cognitum Seed IoT — trust scoring, anomaly detection, fleet management
ruflo-neural-trader neural-trader — 4 agents, LSTM/Transformer, Rust/NAPI backtesting, 112+ MCP tools
ruflo-market-data Market data ingestion, OHLCV vectorization, pattern matching
Use Case Plugins
Feature development ruflo-core + ruflo-swarm + ruflo-testgen + ruflo-ddd
Security audit ruflo-core + ruflo-security-audit + ruflo-aidefence
Architecture work ruflo-core + ruflo-adr + ruflo-ddd + ruflo-sparc
Deep research ruflo-core + ruflo-goals + ruflo-rag-memory + ruflo-intelligence
Vector search ruflo-core + ruflo-ruvector + ruflo-rag-memory + ruflo-knowledge-graph
IoT development ruflo-core + ruflo-iot-cognitum + ruflo-agentdb
Trading systems ruflo-core + ruflo-neural-trader + ruflo-market-data + ruflo-ruvector
Full stack All 32 plugins

npm Package Integration

Several plugins wrap standalone npm packages for deeper functionality:

Plugin npm Package What It Adds
ruflo-neural-trader neural-trader 112+ MCP tools, Rust/NAPI engine, LSTM/Transformer models
ruflo-ruvector ruvector 103 MCP tools, FlashAttention-3, Graph RAG, Brain AGI
# Install backing packages
npm install neural-trader ruvector

# Add as MCP servers (optional, for direct tool access)
claude mcp add neural-trader -- npx neural-trader mcp start
claude mcp add ruvector -- npx ruvector mcp start

Plugin Structure

Each plugin follows the Claude Code plugin specification:

ruflo-<name>/
  .claude-plugin/plugin.json    # Plugin manifest
  agents/<name>.md              # Agent definitions (frontmatter: name, description, model)
  commands/<name>.md            # CLI command mappings
  skills/<name>/SKILL.md        # Interactive skills (frontmatter: name, description, argument-hint, allowed-tools)
  README.md                     # Plugin documentation

Creating a Plugin

claude --plugin-dir plugins/ruflo-plugin-creator
# Then: /create-plugin my-new-plugin

Or manually: copy any existing plugin directory and modify.

Validation

claude plugin validate plugins/ruflo-<name>

Verification & Discoverability

Every MCP tool description across the 32 plugins must answer "use this over native (Bash/Read/Grep/Glob/Task/TodoWrite) when?" per ADR-112. The rule is enforced by CI:

# Run the audit (scans all MCPTool definitions across all plugins)
node scripts/audit-tool-descriptions.mjs

# Gates: every description must include "Use when …" guidance,
# be ≥ 80 chars, and be unique. Baseline at verification/mcp-tool-baseline.json
# is monotone-decreasing — CI fails on any regression.

Combined with verification/ (Ed25519-signed witness manifest, 103+ documented fixes attested), the plugin surface is regression-protected at three layers: install smoke (npm i), behavioral smoke (paired-tool round-trips), and presence attestation (every load-bearing line of every documented fix). See verification/README.md for the full stack.

License

MIT