Multi-agent orchestration CLI for Claude Code — declarative TOML workflows, autonomous agents, context-compression recovery, inter-agent mail.
This repository also configures its own agents. See what agentfactory tells them →
Hook Claude Code
One of 10 in settings.json
Runs before the agent uses a tool for Bash, Write, Edit, Task and Agent tool calls, running an inline shell check (2 commands). From stempeck/agentfactory.
Hook Claude Code
One of 10 in settings.json
Runs when a session starts, running an inline shell check (3 commands). From stempeck/agentfactory.
Hook Claude Code
One of 10 in settings.json
Runs before the context is compacted, running an inline shell check. From stempeck/agentfactory.
Hook Claude Code
One of 10 in settings.json
Runs when you submit a prompt, before the agent sees it, running an inline shell check. From stempeck/agentfactory.
Hook Claude Code
One of 10 in settings.json
Runs when the agent finishes a response, executing quality-gate.sh and fidelity-gate.sh (2 commands). From stempeck/agentfactory.
Hook Claude Code
One of 10 in settings.json
Runs after a tool call finishes for Task and Agent tool calls, running an inline shell check. From stempeck/agentfactory.
Hook Claude Code
One of 10 in settings.json
Runs when a subagent finishes, running an inline shell check. From stempeck/agentfactory.
Hook Claude Code
One of 10 in settings.json
Runs when the agent asks permission for an action, running an inline shell check. From stempeck/agentfactory.
Hook Claude Code
One of 10 in settings.json
Runs when the agent asks you a question, running an inline shell check. From stempeck/agentfactory.
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: