BeforeModel
313Hook Claude Code
One of 5 in hooks.json
Runs on the BeforeModel event, executing tmux_manager.py, keyword_detector.py, intent_gate.py and model_router.py via python3 (4 commands). From pangelini777/oh-my-gem.
Shell commands your agent runs at defined points. A hook is code, so read it before you install it.
Hook Claude Code
One of 5 in hooks.json
Runs on the BeforeModel event, executing tmux_manager.py, keyword_detector.py, intent_gate.py and model_router.py via python3 (4 commands). From pangelini777/oh-my-gem.
Hook Claude Code
One of 4 in hooks.json
Runs after a tool call finishes for Edit, Write, MultiEdit, NotebookEdit and Bash tool calls, executing sg-python.sh via bash (6 commands). From ronmkr/PromptBook.
AlteredCraft/context-engineering-workshop-00
Hook Claude Code
One of 3 in settings.json
Runs after a tool call finishes for Edit, Write and MultiEdit tool calls, executing lint-on-edit.sh via bash. From AlteredCraft/context-engineering-workshop-00.
swesmith/davila7__claude-code-templates.734b8a50
Hook Claude Code
One of 5 in settings.json
Runs after a tool call finishes for Write, Edit, MultiEdit, Write, Edit, MultiEdit, Write, Edit, MultiEdit, Write, Edit and MultiEdit tool calls, running an inline shell check (4 commands). From swesmith/davila7__claude-code-templates.734b8a50.
Hook Claude Code
One of 5 in settings.json
Runs before the agent uses a tool for Bash, Write, Edit, NotebookEdit, Read, Workflow, Bash, Bash, Bash and Bash tool calls, executing dispatch-bash.py, write-under-roots.py, read-guard.py, deny-review-in-workflow.py, ask-prose-claims.py, require-case-list.py, check-staged-code.py and require-run-log-complete.py (8…
Hook Claude Code
One of 5 in settings.json
Runs when a session starts, executing herdr-agent-state.sh via bash (2 commands). From feelepxyz/dotfiles.
Hook Claude Code
Runs when a session starts, executing af-preflight.sh via bash. From sachiniyer/agent-factory.
Hook Claude Code
One of 5 in settings.json
Runs after a tool call finishes for Bash and Write tool calls, executing hook-gate.sh (3 commands). From poseljacob/hq.
cwoodruff/dotnet-claude-workshop-content
Hook Claude Code
One of 4 in settings.json
Runs after a tool call finishes for Write and Edit tool calls, executing dotnet-post-write.sh. From cwoodruff/dotnet-claude-workshop-content.
Hook Claude Code
One of 5 in settings.json
Runs when a session starts on startup and resume, executing focus-out-unattached.sh. From hovnatan/dotfiles.
Hook Claude Code
One of 2 in settings.json
Runs when a session starts, running chrome-devtools-axi. From ctt062/dotfiles.
Hook Claude Code
One of 6 in settings.json
Runs before the agent uses a tool for Bash, Write, Edit, MultiEdit, NotebookEdit and Skill tool calls, executing block-dangerous-git.sh, remind-review-gate.sh, remind-load-skills.sh and handoff-signal.sh (5 commands). From PabloCoello/dotmesh.
Hook Claude Code
One of 3 in settings.json
Runs after a tool call finishes for Write, Edit and MultiEdit tool calls, executing auto-format.sh via bash. From fschifone/claude-setup-wizard.
Hook Claude Code
One of 3 in settings.json
Runs when you submit a prompt, before the agent sees it, executing inject-spec.sh and spec-coverage.sh via bash (2 commands). From ferrarimarlon/harness-init.
Hook Claude Code
One of 4 in settings.json
Runs when you submit a prompt, before the agent sees it, running echo TURN PROTOCOL: Execute skill-sweep gates (session-guard. From marvinleonbutlerii/.dotfiles.
Hook Claude Code
One of 8 in settings.json
Runs before the agent uses a tool for Bash tool calls, executing danger-guard.ts and agent-state.sh via npx (2 commands). From mike-shevchuk/dotfiles.
Hook Claude Code
One of 2 in settings.json
Runs after a tool call finishes, executing format.sh. From midori-profile/claudelint.
hackersandwizards/factory-workshop-excercises
Hook Claude Code
One of 3 in settings.json
Runs when a session starts, running beans prime. From hackersandwizards/factory-workshop-excercises.
TrevorEdris/fellowship-of-the-workflows
Hook Claude Code
One of 4 in hooks.json
Runs before the agent uses a tool for Bash, Read, Edit, Write and Bash tool calls, executing block-dangerous-commands.js and protect-secrets.js (2 commands). From TrevorEdris/fellowship-of-the-workflows.
Hook Claude Code
Runs when a session starts, executing session-start.sh via bash. From vignesh2027/AI-AGENT-SKILLS.
Hook Claude Code
One of 10 in hooks.json
Runs when a session starts, executing heartbeat.sh, warn.sh and hook.sh (3 commands). From rogue-security/rogue-plugins.
Hook Claude Code
One of 2 in hooks.json
Runs when a session starts on startup, resume and clear, executing codex-runtime.js via node. From jacexh/skill-workshop.
Hook Claude Code
One of 3 in settings.json
Runs after a tool call finishes for Edit, Write, MultiEdit and NotebookEdit tool calls, executing decky-claude-hook.mjs via node with --match, --message and --run (3 commands). From qd313/decky-plugin-studio.
Hook Claude Code
Runs before the agent uses a tool for ^apply_patch$ tool calls, executing pre-edit-check.mjs via node. From workspace-json/codex-mcp.
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: