Commands
3clyp50
YAML-configured slash commands with text templates or Python hooks, plus an included skill that can create or update command files for you.
Community Plugin Hub
Prompting Plugins
Browse Prompting plugins from the Agent Zero community Plugin Hub.
Showing 10 of 185 plugins
Headroom Context Compression
emasoudy
Automatically compresses tool outputs in your agent conversations using Headroom AI. Saves 50-70% tokens on every agent turn by compressing file reads, command output, search results, and API responses. Works with any LLM provider. Zero configuration needed — install, run setup, done.
RLM
a0-community-plugins
Hybrid recursive language model routing for oversized external context in Agent Zero.
Runtime Cache
linkliti
Makes Agent Zero faster by remembering prompts and state in memory and refreshing them the moment anything changes on disk.
A0 Self-Improvement
TerminallyLazy
A0 Self-Improvement 2.1.1 fixes metadata-only candidate evidence and skips empty RLM calls, with governed replay, canaries, signed promotion, monitoring, and rollback.
Compound Engineering
Jehu
34 compound-engineering skills - brainstorm, plan, debug, review and ship.
Guard System
PaoloC68
Security guards for tool execution and prompt safety. Blocks tools with flagged scan status and detects prompt injection patterns.
Caveman (token-compressed replies)
Olszalsik
Cuts output tokens by roughly 65% while keeping full technical accuracy by having the agent answer in compressed caveman-speak, across six intensity levels including Classical Chinese modes. Toggleable per chat from the WebUI, with live response validation and cumulative token-savings stats.
Misformat Guard
Olszalsik
Repairs misformatted chat-model responses (broken JSON tool requests) with a cheap utility-model call so Agent Zero never stalls or aborts on them. Defensive layers including a tool-repeat guard that breaks the reasoning death-loop where the agent re-emits the same failing tool call dozens of times. No core patch - pure extension hooks, with a live WebUI dashboard and per-agent configuration.
Tiny Router
Nunezchef
Pre-classify every message in <10ms with a local DeBERTa-v3-small ONNX model (44M params). Routes low-value messages (thanks, ok, got it) away from the LLM — saving 30-50% on API costs at zero latency cost.