Shell commands your agent runs at defined points. A hook is code, so read it before you install it.
Hook Claude Code
Runs before the agent uses a tool for ExitPlanMode tool calls, running ERK_HOOK_ID=exit-plan-mode-hook erk exec exit-plan-mode-hook. From dagster-io/dagster.
Hook
Part of claude-seo
Runs after a tool call finishes for Edit and Write tool calls, running node. From AgriciDaniel/claude-seo.
Hook Claude Code
Runs after a tool call finishes for Write, Edit and MultiEdit tool calls, executing post-edit-format.sh with --show-toplevel. From spree/spree.
Hook Claude Code
Runs before the agent uses a tool for Bash tool calls, executing pre-commit-gate.sh with --show-toplevel. From spree/spree.
Hook Claude Code
Runs before the agent uses a tool for Bash, Edit and Write tool calls, executing generate_entity_index.py with --no-verify (5 commands). From open-metadata/OpenMetadata.
Hook Claude Code
Runs after a tool call finishes for Edit and Write tool calls, running an inline shell check. From open-metadata/OpenMetadata.
Hook
Part of openmetadata-skills
Runs when a session starts, running an inline shell check. From open-metadata/OpenMetadata.
Hook
Part of claude-obsidian
Runs when a session starts on startup, resume, clear and compact, running python3. From AgriciDaniel/claude-obsidian.
Hook
Part of claude-obsidian
Runs when the agent finishes a response, running python3. From AgriciDaniel/claude-obsidian.
Hook Claude Code
Runs when a session starts on startup, clear and compact, executing session-start.py via python3 (3 commands). From mindfold-ai/Trellis.
Hook Claude Code
Runs before the agent uses a tool for Task and Agent tool calls, executing inject-subagent-context.py via python3 (2 commands). From mindfold-ai/Trellis.
Hook Claude Code
Runs when you submit a prompt, before the agent sees it, executing inject-workflow-state.py via python3. From mindfold-ai/Trellis.
Hook Claude Code
Runs after a tool call finishes for Edit, Write and MultiEdit tool calls, executing format.sh. From coder/coder.
Hook Claude Code
Runs when you submit a prompt, before the agent sees it, running lat hook claude UserPromptSubmit. From fathah/hermes-desktop.
Hook Claude Code
Runs when the agent finishes a response, running lat hook claude Stop. From fathah/hermes-desktop.
Hook Claude Code
Runs before the agent uses a tool for Bash tool calls, executing deny-git-no-verify.sh. From datahub-project/datahub.
Hook
Runs when a session starts, executing session-context-wrapper.sh. From EverMind-AI/EverOS.
Hook
Runs when you submit a prompt, before the agent sees it, executing inject-memories.js. From EverMind-AI/EverOS.
Hook
Runs when a session ends, executing session-summary.js. From EverMind-AI/EverOS.
Hook Claude Code
Runs when a session starts, executing setup-code-signing.sh via bash. From rommapp/romm.
Hook
Part of ifixai
Runs when a session starts, running python3. From ifixai-ai/iFixAi.
Hook
Part of semantica
Runs after a tool call finishes for Write, Edit, Write and Edit tool calls, running an inline shell check (2 commands). From semantica-agi/semantica.
Hook
Part of semantica
Runs before the agent uses a tool for Bash tool calls, running an inline shell check. From semantica-agi/semantica.
Hook Claude Code
Runs after a tool call finishes for Edit and Write tool calls, executing docs-build-check.sh and py-typecheck-flag.sh (2 commands). From cocoindex-io/cocoindex.
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: