425 tagged agents, measured the same way as everything else here.
Browse within: agentic-workflow 33hooks 26codex-cli 19Multi-Agent 16gemini 16agentic 15atif 14atof 14claude-code-skills 14coding 14dotfiles 14agentmemory 12claudecode 12markdown 12
dralgorhythm/claude-agentic-framework
Hook Claude Code
Part of claude-agentic-framework
Runs after a tool call finishes for Edit, MultiEdit and Write tool calls, executing post-tool-use-tracker.sh and post-edit-lint.sh (2 commands). From dralgorhythm/claude-agentic-framework.
Hook
Part of pi
Runs when the agent finishes a response, executing capture-decision.sh via bash. From share-skills/pi.
Hook
Part of pi
Runs after a tool call finishes for Bash tool calls, executing capture-tool-result.sh via bash. From share-skills/pi.
Hook
Part of pi
Runs when a tool call fails for Bash tool calls, executing capture-tool-result.sh via bash. From share-skills/pi.
Hook Claude Code
Runs when a session ends, executing social_mcp_daemon.sh via bash. From lxinfei5/research-os.
Hook
Part of overclick
Runs when a session starts on startup, resume, clear and compact, executing session-start.mjs via node. From ustoppble/overclick.
Hook
Part of overclick
Runs after a tool call finishes for task_claim, mcp__.*__task_claim, task_deliver, mcp__.*__task_deliver, task_release, mcp__.*__task_release, task_deliver and mcp__.*__task_deliver tool calls, executing claim-guard.mjs and post-deliver.mjs via node (2 commands). From ustoppble/overclick.
Hook
Part of overclick
Runs before the agent uses a tool for task_create and mcp__.*__task_create tool calls, executing pre-create.mjs and claim-guard.mjs via node (2 commands). From ustoppble/overclick.
Hook Claude Code
Runs after a tool call finishes for Edit(*), Write(*), Bash(git commit:*) and Bash(mnemosyne remember:*) tool calls, executing post-tool-use.sh, post-commit.sh and post-memory-store.sh (5 commands). From rand/mnemosyne.
Hook Claude Code
Runs before the agent uses a tool for Bash(git push:*) and Bash(gh pr create:*) tool calls, executing pre-destructive.sh (2 commands). From rand/mnemosyne.
Hook Claude Code
Runs before the context is compacted, executing pre-compact.sh. From rand/mnemosyne.
Hook
Part of gangsta
Runs when a session starts on startup, clear and compact, executing run-hook.cmd. From kucherenko/gangsta.
Hook
Part of lucid
Runs when a session starts, running an inline shell check. From get-Lucid/Lucid.
Hook Claude Code
Runs to expand your prompt before the agent sees it, executing bridge.js via node. From crystian/skill-map.
Hook Claude Code
Runs before the agent uses a tool for ^(Skill, Agent, Read, Write, Edit and mcp__.+)$ tool calls, executing bridge.js via node. From crystian/skill-map.
Hook Claude Code
Runs after a tool call finishes for ^Agent$ tool calls, executing bridge.js via node. From crystian/skill-map.
Hook Claude Code
Runs when a session starts, executing session-start.sh. From matteing/opal.
Hook Claude Code
Runs when a session starts, executing session-start.sh. From tuanductran/hr-skills.
Hook Claude Code
Runs before the agent uses a tool for Bash tool calls, executing block-push-to-main.sh. From tuanductran/hr-skills.
Hook Claude Code
Runs after a tool call finishes for Write, Edit and MultiEdit tool calls, executing post-edit-markdown.sh, post-edit-typescript.sh, post-edit-evals.sh and post-edit-tests.sh (4 commands). From tuanductran/hr-skills.
Hook Claude Code
Runs after a tool call finishes for Bash tool calls, executing memory-capture.sh via bash. From roberto-mello/lavra.
Hook Claude Code
Runs when a session starts, executing auto-recall.sh via bash (2 commands). From roberto-mello/lavra.
Hook Claude Code
Runs when a subagent finishes, executing subagent-wrapup.sh via bash. From roberto-mello/lavra.
Hook
Part of learning-agents
Runs after a tool call finishes for Task tool calls, executing post_task.sh. From Unsupervisedcom/deepwork.
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: