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

rUvedf172876086
diff --git a/AGENTS.md b/AGENTS.md
index bdfd87e083..932df56e38 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -46,15 +46,15 @@
## Concurrency: 1 MESSAGE = ALL RELATED OPERATIONS
-- All operations MUST be concurrent/parallel in a single message
-- Use Task tool for spawning agents, not just MCP
+- All operations MUST be concurrent/parallel when possible
+- Use CLI commands for spawning agents
**Mandatory patterns:**
-- ALWAYS batch ALL todos in ONE call (5-10+ minimum)
-- ALWAYS spawn ALL agents in ONE message with full instructions via Task tool
-- ALWAYS batch ALL file reads/writes/edits in ONE message
-- ALWAYS batch ALL terminal operations in ONE message
-- ALWAYS batch ALL memory store/retrieve operations in ONE message
+- ALWAYS batch related operations together
+- Use `npx claude-flow agent spawn` for agent creation
+- ALWAYS batch file reads/writes/edits together
+- ALWAYS batch terminal operations together
+- ALWAYS batch memory store/retrieve operations together
---