π The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
TypeScript agentic-aiagentic-frameworkagentic-workflowagentsai-agentsai-assistantai-skillsautonomous-agentsclaudecodexdsh-pluginharnessmcp-servermulti-agentmulti-agent-systemsnpmskillsswarmswarm-intelligencetypescript
Checkpoint: File edits
rUv18b279781b4c
diff --git a/v3/@claude-flow/cli/README.md b/v3/@claude-flow/cli/README.mdindex 94e0e198b0..d4136492ec 100644--- a/v3/@claude-flow/cli/README.md+++ b/v3/@claude-flow/cli/README.md@@ -500,9 +500,12 @@ npm install -g claude-flow@alpha --omit=optional### Basic Usage```bash-# Initialize project+# Initialize project (standard template)npx claude-flow@alpha init+# Initialize with wizard (interactive template selection)+npx claude-flow@alpha init --wizard+# Start MCP server for Claude Code integrationnpx claude-flow@alpha mcp start@@ -513,6 +516,41 @@ npx claude-flow@alpha --agent coder --task "Implement user authentication"npx claude-flow@alpha --list```+<details>+<summary><b>CLAUDE.md Init Templates</b></summary>++The `init` command generates a CLAUDE.md file that configures Claude Code behavior. Choose a template based on your use case:++| Template | Score | Lines | Use Case |+|----------|-------|-------|----------|+| `minimal` | 93/100 (A) | ~140 | Quick start β behavioral rules, anti-drift, CLI reference |+| `standard` | 93/100 (A) | ~190 | **Recommended** β swarm orchestration, agents, memory commands |+| `full` | 91/100 (A) | ~295 | Everything β hooks, learning protocol, intelligence system |+| `security` | 93/100 (A) | ~205 | Security-focused β scanning, audit protocols, CVE checks |+| `performance` | 95/100 (A) | ~225 | Performance-focused β benchmarking, profiling, optimization |+| `solo` | 93/100 (A) | ~145 | Solo developer β no swarm overhead, simple agent usage |++All templates are analyzer-validated with **100% enforceability** and **A-grade** governance scores.++**Template selection:**+- Interactive: `npx claude-flow@alpha init --wizard` (prompts for template choice)+- Programmatic: Set `runtime.claudeMdTemplate` in your init options+- Default: `standard` template when components include agents/commands, `minimal` otherwise++**Governance validation:**+```bash+# Analyze your CLAUDE.md quality and enforceability+npx claude-flow@alpha guidance analyze++# Optimize for higher score+npx claude-flow@alpha guidance optimize --apply++# Run A/B comparison test+npx claude-flow@alpha guidance ab-test --config-a original.md --config-b optimized.md+```++</details>+### Upgrading```bash