Agent Claude Code
System prompt for creating custom AI agents with detailed specifications.
CLI is all you need. The agent CLI harness.
ConnectOnion is an open-source, template-first toolkit for building, debugging, deploying, and operating AI agents. Developers use its command-line tools and Python runtime to create agents, add tools, connect services, deploy them, and make them callable by other agents, while the catalogue entries are related agents, skills, and instructions.
This repository also configures its own agents. See what connectonion tells them →
Agent Claude Code
System prompt for creating custom AI agents with detailed specifications.
Agent Claude Code
Prompt for an 'agent hook'.
Agent Claude Code
Reviews and critiques user-defined auto mode classifier rules for clarity, completeness, conflicts, and actionability.
Agent Claude Code
Instructions for generating clear, concise command descriptions in active voice for bash commands.
Agent Claude Code
System prompt for detecting command prefixes and command injection.
Agent Claude Code
Instructions for orchestrating a large, parallelizable change across a codebase.
Agent Claude Code
System prompt for the claude-guide agent that helps users understand and use Claude Code, the Claude Agent SDK and the Claude API effectively.
Agent Claude Code
System prompt for analyzing codebases and creating CLAUDE.md documentation files.
Agent Claude Code
Generates a title for the coding session.
Agent Claude Code
System prompt for creating detailed conversation summaries.
Agent Claude Code
Agent for determining which memory files to attach for the main agent.
Agent Claude Code
Instructs an agent to perform a multi-phase memory consolidation pass — orienting on existing memories, gathering recent signal from logs and transcripts, merging updates into topic files, and pruning the index.
Agent Claude Code
System prompt for the Explore subagent.
Agent Claude Code
System prompt for evaluating hook conditions in Claude Code.
Agent Claude Code
Enhanced prompt for the Plan subagent.
Agent Claude Code
System prompt for fetching and displaying GitHub PR comments.
Agent Claude Code
V2 instructions for generating prompt suggestions for Claude Code.
Agent Claude Code
Streamlined prompt for creating a single git commit with pre-populated context.
Agent Claude Code
Streamlined prompt for creating a commit and pull request with pre-populated context.
Agent Claude Code
Agent prompt used for summarizing recent messages.
Agent Claude Code
System prompt for reviewing GitHub pull requests with code analysis.
Agent Claude Code
Guides the user through scheduling, updating, listing, or running remote Claude Code agents on cron triggers via the Anthropic cloud API.
Agent Claude Code
Instructs Claude to act as a security monitor that evaluates autonomous coding agent actions against block/allow rules to prevent prompt injection, scope creep, and accidental damage.
Agent Claude Code
Defines the environment context, block rules, and allow exceptions that govern which tool actions the agent may or may not perform.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: