Skip to content

armgit / ruflo

Public Imported from GitHub
0

🌊 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

Checkpoint: File edits

rUv88843884e030
diff --git a/v3/@claude-flow/cli/.claude/commands/swarm/swarm.md b/v3/@claude-flow/cli/.claude/commands/swarm/swarm.md
index 6912c41629..8e510e3101 100644
--- a/v3/@claude-flow/cli/.claude/commands/swarm/swarm.md
+++ b/v3/@claude-flow/cli/.claude/commands/swarm/swarm.md
@@ -1,4 +1,4 @@
-# swarm
+# /swarm
Main swarm orchestration command for Claude Flow V3.
@@ -8,51 +8,80 @@ Main swarm orchestration command for Claude Flow V3.
1. **Spawn ALL agents in background** using `run_in_background: true`
2. **Put ALL Task calls in ONE message** for parallel execution
-3. **Tell user what's happening** with clear agent list
+3. **Display status board** with ASCII table and emojis
4. **STOP and WAIT** - don't add more tool calls or poll status
+## βœ… CORRECT Spawn Pattern
+
```javascript
-// βœ… CORRECT: Background parallel agents in ONE message
+// Spawn ALL agents IN BACKGROUND in ONE message
Task({ prompt: "Research...", subagent_type: "researcher", run_in_background: true })
-Task({ prompt: "Code...", subagent_type: "coder", run_in_background: true })
+Task({ prompt: "Design...", subagent_type: "architect", run_in_background: true })
+Task({ prompt: "Implement...", subagent_type: "coder", run_in_background: true })
Task({ prompt: "Test...", subagent_type: "tester", run_in_background: true })
-
-// Then TELL USER and STOP:
-"I've launched 3 agents working in parallel. They'll report when done."
+Task({ prompt: "Review...", subagent_type: "reviewer", run_in_background: true })
```
-```javascript
-// ❌ WRONG: Don't poll or check status
-TaskOutput({ task_id: "..." }) // NO!
-swarm status // NO!
-"Should I check on the agents?" // NO!
+## πŸ“Š Required Status Display (ASCII Table)
+
+**After spawning, Claude Code MUST display this status board:**
+
+```
+╔══════════════════════════════════════════════════════════════╗
+β•‘ 🐝 SWARM LAUNCHED β•‘
+╠══════════════════════════════════════════════════════════════╣
+β•‘ πŸ“‹ Task: [user's task description] β•‘
+β•‘ πŸ”„ Topology: hierarchical β”‚ πŸ‘₯ Agents: 5/15 β•‘
+╠══════════════════════════════════════════════════════════════╣
+β•‘ AGENT β”‚ STATUS β”‚ TASK β•‘
+╠══════════════════════════════════════════════════════════════╣
+β•‘ πŸ” Researcher β”‚ 🟒 ACTIVE β”‚ Analyzing requirements β•‘
+β•‘ πŸ—οΈ Architect β”‚ 🟒 ACTIVE β”‚ Designing approach β•‘
+β•‘ πŸ’» Coder β”‚ 🟒 ACTIVE β”‚ Implementing solution β•‘
+β•‘ πŸ§ͺ Tester β”‚ 🟒 ACTIVE β”‚ Writing tests β•‘
+β•‘ πŸ‘€ Reviewer β”‚ 🟒 ACTIVE β”‚ Code review & security β•‘
+╠══════════════════════════════════════════════════════════════╣
+β•‘ ⏳ Working in parallel... Results will arrive automatically β•‘
+β•šβ•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•
```
-## Usage
-```bash
-npx @claude-flow/cli@latest swarm <objective> [options]
+## ❌ DO NOT
+
+```
+TaskOutput({ task_id: "..." }) // ❌ Don't poll
+"Should I check on agents?" // ❌ Don't ask
+swarm status // ❌ Don't check repeatedly
```
-## Options
-- `--strategy <type>` - Execution strategy (research, development, analysis, testing)
-- `--topology <type>` - Swarm topology (hierarchical, mesh, ring, star)
-- `--max-agents <n>` - Maximum number of agents (default: 15)
-- `--background` - Run agents in background (default: true)
-- `--parallel` - Enable parallel execution (default: true)
+## πŸ“‹ Agent Types by Task
-## Examples
+```
+╔═══════════════════╦═════════════════════════════════════════════╗
+β•‘ TASK TYPE β•‘ AGENTS β•‘
+╠═══════════════════╬═════════════════════════════════════════════╣
+β•‘ πŸ†• New Feature β•‘ researcher, architect, coder, tester, rev β•‘
+β•‘ πŸ› Bug Fix β•‘ researcher, coder, tester β•‘
+β•‘ ♻️ Refactor β•‘ architect, coder, reviewer β•‘
+β•‘ πŸ”’ Security β•‘ security-architect, auditor, reviewer β•‘
+β•‘ ⚑ Performance β•‘ researcher, perf-engineer, coder β•‘
+β•‘ πŸ“š Documentation β•‘ researcher, api-docs β•‘
+β•šβ•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•©β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•
+```
+
+## Usage
```bash
-# Initialize swarm
npx @claude-flow/cli@latest swarm init --topology hierarchical
-
-# Check status (ONLY when agents complete)
-npx @claude-flow/cli@latest swarm status
+npx @claude-flow/cli@latest swarm status # Only after completion
```
-## Agent Types by Task
-| Task | Agents |
-|------|--------|
-| New Feature | researcher, architect, coder, tester, reviewer |
-| Bug Fix | researcher, coder, tester |
-| Refactor | architect, coder, reviewer |
-| Security | security-architect, security-auditor, reviewer |
+## Options
+```
+╔════════════════════════╦═══════════════════════════════════════╗
+β•‘ OPTION β•‘ DESCRIPTION β•‘
+╠════════════════════════╬═══════════════════════════════════════╣
+β•‘ --strategy <type> β•‘ research, development, analysis β•‘
+β•‘ --topology <type> β•‘ hierarchical, mesh, ring, star β•‘
+β•‘ --max-agents <n> β•‘ Maximum agents (default: 15) β•‘
+β•‘ --background β•‘ Run in background (default: true) β•‘
+β•šβ•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•©β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•
+```