Agent Claw V2
agent-claw-v2
v0.2.0May 25, 2026Multi-agent orchestration — supervisor/worker patterns, planning loops, context passing, and production deployment
Agent v1 was a sketch; v2 is production. I handle multi-agent orchestration — supervisor routing, Delegate-Execute-Verify chains, agent-to-agent protocol contracts with schema-validated message passing, and hierarchical planning where a top-level planner decomposes goals into subtask DAGs. I care about agent handoff fidelity: when one agent delegates to another, does the context survive intact? I measure knowledge transfer accuracy, inter-agent latency, and decision reversibility. I generate swarm topology diagrams, delegation protocol specs, and orchestration dashboards with per-agent health metrics.
OpenClaw
Hermes
Claude Code
Codex
Cursor
Windsurf
Aider
OllamaPRIMARY ACTION
Unlock with ProWhen to Use
- Run local models with private workflows
- Tune inference for local hardware
- Choose effective GGUF variants
- Benchmark practical latency and quality
Compatible Frameworks
OpenClawHermesClaude CodeCodexCursorWindsurfAiderOllama8 TOOLS
Quality Gates
- no fake claims
- tool use protocols defined
- planning loops documented
- memory persistence verified
4 GATES DEFINED
Expected Outputs
Native exports per tool
openclaw/AGENTS.mdopenclaw/SOUL.mdopenclaw/TOOLS.md+7 morehermes/skills/flickclaw/agent-claw-v2/SKILL.mdhermes/skills/flickclaw/agent-claw-v2/references/workflow.mdhermes/skills/flickclaw/agent-claw-v2/references/quality-gates.md+2 moreclaude-code/CLAUDE.mdclaude-code/.claude/skills/agent-claw-v2/SKILL.mdclaude-code/.claude/skills/agent-claw-v2/references/workflow.md+3 morecodex/AGENTS.mdcodex/.flickclaw/agents/agent-claw-v2/codex.mdcodex/.flickclaw/agents/agent-claw-v2/workflow.md+2 morecursor/.cursor/rules/flickclaw-agent-claw-v2.mdccursor/.cursor/rules/flickclaw-agent-claw-v2-workflow.mdccursor/.cursor/rules/flickclaw-agent-claw-v2-quality-gates.mdcwindsurf/.windsurf/rules/flickclaw-agent-claw-v2.mdwindsurf/.windsurf/rules/flickclaw-agent-claw-v2-workflow.mdwindsurf/.windsurf/rules/flickclaw-agent-claw-v2-quality-gates.mdaider/CONVENTIONS.mdaider/aider.mdaider/.aider.conf.ymlollama/Modelfileollama/system-prompt.mdollama/template.md+1 moreInstall Commands
Install the FlickClaw CLI, then select your AI agent framework below to get the correct install command.
Step 1: Install CLI (one-time)
npm install -g @flickclaw/cli@latestStep 2: Select Framework
npm exec --yes @flickclaw/cli@latest -- install agent-claw-v2 --target openclawDownload as ZIP
Example Prompt
Try this prompt with Agent Claw V2 to see what it can do:
Optimize the local model setup for performance. Benchmark current config and suggest improvements for Swarm Topology Diagram with Agent Roles and Communication Edges, Delegation Protocol Specification with Message Schema Contract, Multi-Agent Orchestration Dashboard with Per-Agent Health Metrics.Example Output
IllustrativeWhat a typical Agent Claw V2 report looks like:
# Agent Claw V2 — Assessment Report **Project**: ollama-deployment **Context**: a local LLM deployment running Llama 3.1 8B on consumer GPU hardware **Generated**: 2026-07-10 ## Executive Summary The Agent Claw V2 completed its review of ollama-deployment (a local LLM deployment running Llama 3.1 8B on consumer GPU hardware). 3 findings were identified with concrete remediation steps. All quality gates were verified before delivery. ## Findings | # | Severity | Area | Finding | Recommended Action | |---|----------|------|---------|-------------------| | 1 | **P1** | Performance | Inference latency spikes to 8s under concurrency | Enable continuous batching and set max_batch=4 | | 2 | **P2** | Memory | Model consumes 18GB VRAM, headroom insufficient | Switch to Q4_K_M quantization, target <12GB | | 3 | **P2** | Setup | No Modelfile with system prompt defined | Create Modelfile with role, constraints, and templates | ## Quality Gates - [✓] delegation_context_fidelity_test - [✓] agent_protocol_schema_validation - [✓] hierarchical_plan_dag_complete ## Outputs Generated - **Swarm Topology Diagram with Agent Roles and Communication Edges**: Included in the report above. - **Delegation Protocol Specification with Message Schema Contract**: Included in the report above. - **Multi-Agent Orchestration Dashboard with Per-Agent Health Metrics**: Included in the report above. - **Context-Fidelity Test Report with Knowledge Transfer Accuracy Score**: Included in the report above. ## Validation - [x] All quality gates passed (3/3) - [x] 3 findings documented with severity and remediation - [x] 4 output sections generated - [x] Evidence collected and referenced --- *This is an illustrative example output from FlickClaw. Results vary based on project context.*