Hooks

Shell commands your agent runs at defined points. A hook is code, so read it before you install it.

PostToolUse

457

wednesday-solutions/ai-agent-skills

Hook Claude Code

One of 2 in settings.json

Runs after a tool call finishes for Write and Edit tool calls, running an inline shell check. From wednesday-solutions/ai-agent-skills.

not rated 168 3mo ago A tokens not measured original MIT

UserPromptSubmit

458

KimYx0207/Kim_Service

Hook Claude Code

One of 2 in settings.json

Runs when you submit a prompt, before the agent sees it, running node. From KimYx0207/Kim_Service.

not rated 168 +1 24d ago A tokens not measured original MIT

PostToolUse

459

confluentinc/mcp-confluent

Hook Claude Code ✓ vendor

One of 2 in settings.json

Runs after a tool call finishes for Edit and Write tool calls, running an inline shell check. From confluentinc/mcp-confluent.

not rated 167 yesterday A tokens not measured original MIT

PostToolUse

460

DefangLabs/defang

Hook Claude Code

One of 2 in settings.json

Runs after a tool call finishes for Edit and Write tool calls, running an inline shell check. From DefangLabs/defang.

not rated 167 +3 today A tokens not measured original MIT

PostToolUse

461

outlmd/outl

Hook Claude Code

One of 3 in settings.json

Runs after a tool call finishes for Edit and Write tool calls, executing rust-quality.sh, file-size-guard.sh, catalog-sync-guard.sh, doc-sync-guard.sh, markdown-size-guard.sh, semantic-linebreak-guard.sh and section-ref-guard.sh (7 commands). From outlmd/outl.

not rated 167 +6 yesterday A tokens not measured copy · 50% MIT

PostToolUse

462

nteract/nteract

Hook Claude Code

One of 3 in settings.json

Runs after a tool call finishes for Write and Edit tool calls, running an inline shell check. From nteract/nteract.

not rated 166 +2 yesterday A tokens not measured original BSD-3-Clause

PreToolUse

463

vericontext/vibeframe

Hook Claude Code

One of 3 in settings.json

Runs before the agent uses a tool for Bash tool calls, executing pre-push-validate.sh via bash. From vericontext/vibeframe.

not rated 165 1mo ago A tokens not measured original MIT

PreToolUse

464

paiml/paiml-mcp-agent-toolkit

Hook Claude Code

One of 2 in settings.json

Runs before the agent uses a tool for Write and Edit tool calls, executing pmat-quality-feedback.sh. From paiml/paiml-mcp-agent-toolkit.

not rated 164 +1 yesterday A tokens not measured original MIT

PreToolUse

465

Khan/wonder-blocks

Hook Claude Code

One of 3 in settings.json

Runs before the agent uses a tool for Bash, Bash and Bash tool calls, executing git-filter.mjs, gh-filter.mjs and echo-banner-filter.mjs (3 commands). From Khan/wonder-blocks.

not rated 163 yesterday A tokens not measured original MIT

PreToolUse

466

AgiFlow/aicode-toolkit

Hook Claude Code

One of 6 in settings.json

Runs before the agent uses a tool, executing cli.ts via bun with --type (2 commands). From AgiFlow/aicode-toolkit.

not rated 162 +1 1mo ago A tokens not measured AGPL-3.0

PostToolUse

467

daiki-beppu/youtube-automation

Hook Claude Code

One of 5 in settings.json

Runs after a tool call finishes for Bash, Task, Agent, Workflow, Edit, Write and NotebookEdit tool calls, running an inline shell check (4 commands). From daiki-beppu/youtube-automation.

not rated 162 +1 changed 2d ago A tokens not measured

PostToolUse

468

workersio/skills

Hook Claude Code

One of 2 in settings.json

Runs after a tool call finishes for Edit, Write and MultiEdit tool calls, executing test-review-reminder.py via python3 with --show-toplevel. From workersio/skills.

not rated 161 +2 1mo ago A tokens not measured original MIT

PreToolUse

469

idavidov13/agentic-playwright

Hook Claude Code

One of 2 in settings.json

Runs before the agent uses a tool for Write, Edit and MultiEdit tool calls, executing enforce_constitution.py via python3. From idavidov13/agentic-playwright.

not rated 161 +27 2d ago A tokens not measured original MIT

PostToolUse

470

notactuallytreyanastasio/deciduous

Hook Claude Code

One of 3 in settings.json

Runs after a tool call finishes for Bash tool calls, executing post-commit-reminder.sh. From notactuallytreyanastasio/deciduous.

not rated 160 yesterday A tokens not measured original Apache-2.0

PostToolUse

471

jongwony/epistemic-protocols

Hook Claude Code

One of 2 in settings.json

Runs after a tool call finishes for Bash tool calls, executing claude_dispatcher.mjs via node. From jongwony/epistemic-protocols.

not rated 160 today A tokens not measured original MIT

Notification

472

codingagentsystem/cas

Hook Claude Code

One of 12 in settings.json

Runs when the agent sends a notification for permission_prompt, idle_prompt and auth_success tool calls, running cas hook Notification. From codingagentsystem/cas.

not rated 160 +9 5mo ago A tokens not measured original MIT

PostToolUse

473

kryptobaseddev/cleo

Hook Claude Code

One of 4 in settings.json

Runs after a tool call finishes for Bash, Edit, Write, MultiEdit, Agent, Task, Write and Edit tool calls, executing gsd-context-monitor.js and gsd-phase-boundary.sh via node (2 commands). From kryptobaseddev/cleo.

not rated 160 16d ago A tokens not measured original MIT

SessionStart

474

joenandez/spectre

Hook Claude Code

Runs when a session starts on startup, resume, clear, compact, startup, clear and compact, executing bootstrap.mjs, handoff-resume.mjs and load-knowledge.mjs via node with --host (3 commands). From joenandez/spectre.

not rated 158 +2 yesterday A tokens not measured original MIT

PostToolUse

475

dcostenco/prism-coder

Hook Claude Code

One of 2 in settings.json

Runs after a tool call finishes for Bash tool calls, executing post-commit-repomix.sh via bash. From dcostenco/prism-coder.

not rated 157 2d ago A tokens not measured original Apache-2.0

PreToolUse

476

dnotitia/akb

Hook Claude Code

One of 5 in settings.json

Runs before the agent uses a tool for Bash, Read, Write, Edit, MultiEdit, mcp__akb__.* and mcp__akb_test__.* tool calls, executing akb_pm_hook.py via python3. From dnotitia/akb.

not rated 157 +2 yesterday A tokens not measured

InstructionsLoaded

477

zeuikli/claude-code-workspace

Hook Claude Code

One of 11 in settings.json

Runs after instructions files are loaded, executing instructions-loaded.sh. From zeuikli/claude-code-workspace.

not rated 155 +1 yesterday A tokens not measured

SessionStart

478

mweinbach/agent-coworker

Hook Claude Code

One of 2 in settings.json

Runs when a session starts on startup and resume, executing cloud_session_start.sh. From mweinbach/agent-coworker.

not rated 155 yesterday A tokens not measured

Stop

479

AratKruglik/claude-laravel

Hook Claude Code

One of 2 in settings.json

Runs when the agent finishes a response, running docker compose exec app composer run pint:fix (2 commands). From AratKruglik/claude-laravel.

not rated 154 4mo ago A tokens not measured

SessionStart

480

P0lar1zzZ/Ombre-Brain

Hook Claude Code

One of 2 in settings.json

Runs when a session starts on startup and resume, executing session_breath.py via python (2 commands). From P0lar1zzZ/Ombre-Brain.

not rated 154 +1 5mo ago A tokens not measured original MIT

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: