Blogs
Stay updated with insights, tips, and strategies from our team. Explore the latest on SEO, digital marketing, link building, and automation.
Hermes agent /busy decides what happens when you message a working agent: queue, steer or interrupt — how each mode behaves and which to default to.
Hermes agent /refine triggers the memory and skill self-improvement review immediately, in a background fork — what it does and when to fire it.
Hermes agent /review spawns an independent reviewer subagent that reads diffs, runs code and reports back — setup, config pinning and best uses.
Hermes agent /plan writes a markdown implementation plan to .hermes/plans/ without executing anything — how it works and why plan-first pays.
Hermes agent /btw answers a quick side question from a read-only snapshot of your session — no interruption, no cache damage. How and when to use it.
Hermes agent /bg runs a prompt in a separate background session so your context stays free — how it works, where results land, and smart uses.
Hermes agent /heartbeat: a recurring prompt that re-enters idle sessions on your interval (60s minimum) — setup, subcommands, and when cron wins.
Hermes agent /goal explained: set a standing objective, let a judge model check completion each turn, and manage it with status, pause and clear.
What is ClawRouter? It’s the agent-native LLM router behind OpenClaw that picks the cheapest capable model in under 1ms. Here’s how it really works.
Hermes group chat rooms arrived with Bot Mode in v0.21.0: named agents, @-mentions and bot-to-bot DMs. Here’s my full setup guide and honest take.
Claude code diff panel explained: toggle /diff (v2.1.260) for a fullscreen live view of uncommitted changes beside the chat as Claude edits files.
Claude code skill doctor guide: run /skill-doctor (v2.1.261) to see what every loaded skill costs in context, spot never-used skills and prune fast.