Building agents hooks

435 tagged Building agents, measured the same way as everything else here.

Browse within: claude-code-plugin 62ai-coding 59ai-development 26claude-ai 26claude-plugin 26agentic-workflow 24langgraph 23ai-tools 22agentic-coding 21copilot 18nextjs 18knowledge-graph 17gemini 16anthropic-claude 15

PreToolUse

49

mendix/web-widgets

Hook Claude Code

One of 3 in settings.json

Runs before the agent uses a tool for Bash, Write, Edit and MultiEdit tool calls, executing validate-openspec-path.sh. From mendix/web-widgets.

not rated 40 yesterday A tokens not measured original Apache-2.0

PreToolUse

50

wildcard/caro

Hook Claude Code

One of 8 in settings.json

Runs before the agent uses a tool for Bash tool calls, executing block-main-commits.sh, worktree-protection.sh and block-budget-leaks.sh (3 commands). From wildcard/caro.

not rated 37 yesterday A tokens not measured AGPL-3.0

UserPromptSubmit

51

daffy0208/ai-dev-standards

Hook Claude Code

One of 3 in settings.json

Runs when you submit a prompt, before the agent sees it, executing context-restore.sh and skill-activation-prompt.sh (2 commands). From daffy0208/ai-dev-standards.

not rated 36 8mo ago A tokens not measured original MIT

PreToolUse

52

anthony-chaudhary/fak

Hook Claude Code

One of 3 in settings.json

Runs before the agent uses a tool for Bash, Read, Write, Edit, MultiEdit, NotebookEdit, Bash, Write, Edit, MultiEdit, NotebookEdit and mcp__.*dos.* tool calls, running fak (2 commands). From anthony-chaudhary/fak.

not rated 36 +4 today A tokens not measured original Apache-2.0

StopFailure

53

kumaran-is/claude-code-onboarding

Hook Claude Code

One of 7 in settings.json

Runs on the StopFailure event, executing stopfailure-api-error-notice.sh. From kumaran-is/claude-code-onboarding.

not rated 35 2mo ago A tokens not measured original MIT

PreToolUse

54

indexedlabs/pydantic-ai-gepa

Hook Claude Code

One of 5 in settings.json

Runs before the agent uses a tool for Edit, Write, Bash and Task tool calls, running mt hooks --event PreToolUse. From indexedlabs/pydantic-ai-gepa.

not rated 34 9d ago A tokens not measured original MIT

PreToolUse

55

MichelKerkmeester/skilled-agent-harness_spec-driven-loops

Hook Claude Code

One of 8 in settings.json

Runs before the agent uses a tool for Bash, Task, Task, Agent, mcp__claude_ai_.*, Write and Edit tool calls, executing dispatch-preflight-lint.mjs, spec-gate-enforce.mjs, git-preflight-advisory.mjs, task-dispatch-guard.cjs, fable-subagent-guard.mjs and mcp-route-guard.cjs via bash (7 commands). From…

not rated 34 today A tokens not measured copy · 100% MIT

PostToolUse

56

mrlm-xyz/demo-claude-marketplace

Hook Claude Code

One of 3 in settings.json

Runs after a tool call finishes for Edit and Write tool calls, executing check-docs-drift.sh. From mrlm-xyz/demo-claude-marketplace.

not rated 34 2d ago A tokens not measured copy · 52% Apache-2.0

SessionStart

57

kupzed/catatz

Hook Claude Code

One of 6 in settings.json

Runs when a session starts on startup, resume, clear and compact, executing adapter.mjs via node. From kupzed/catatz.

not rated 33 3d ago A tokens not measured original MIT

PreToolUse

58

matteocervelli/llms

Hook Claude Code

One of 4 in settings.json

Runs before the agent uses a tool for Bash, Edit, Write and Read tool calls, executing hook_handler.py via python (3 commands). From matteocervelli/llms.

not rated 25 3mo ago A tokens not measured original MIT

PreCompact

59

dp-web4/SAGE

Hook Claude Code

One of 5 in settings.json

Runs before the context is compacted for manual and auto tool calls, running an inline shell check (2 commands). From dp-web4/SAGE.

not rated 24 today A tokens not measured AGPL-3.0

SessionEnd

60

kangraemin/claude-status-bar

Hook Claude Code

One of 6 in settings.json

Runs when a session ends, executing session-end.sh. From kangraemin/claude-status-bar.

not rated 24 +1 4d ago A tokens not measured copy · 52% MIT

PreToolUse

61

gracefullight/docusaurus-plugins

Hook Claude Code

One of 4 in settings.json

Runs before the agent uses a tool for Bash tool calls, executing oma-hook.sh with --vendor, --event and --matcher. From gracefullight/docusaurus-plugins.

not rated 22 2mo ago A tokens not measured original MIT

SessionStart

62

f-amine/vibe-stack

Hook Claude Code

One of 11 in settings.json

Runs when a session starts, executing hook-handler.cjs and auto-memory-hook.mjs via sh (2 commands). From f-amine/vibe-stack.

not rated 21 2mo ago A tokens not measured copy · 80% MIT

Stop

63

natea/ExoMind

Hook Claude Code

One of 5 in settings.json

Runs when the agent finishes a response, running an inline shell check. From natea/ExoMind.

not rated 21 10mo ago A tokens not measured copy · 86% MIT

PreToolUse

64

heyJordanParker/dotfiles

Hook

One of 2 in hooks.json

Runs before the agent uses a tool for Bash, Write, Edit, MultiEdit and ExitPlanMode tool calls, executing block-git-revert.sh, block-unsafe-delete.sh, validate-planning-docs.sh and validate-plan-quality.sh (4 commands). From heyJordanParker/dotfiles.

not rated 20 6d ago A tokens not measured

PreToolUse

65

DangQuangSE/team-development-skills

Hook Claude Code

One of 8 in settings.json

Runs before the agent uses a tool for Read, Write, Edit, Bash, Write, Edit, Bash, Agent, Write, Write and Edit tool calls, executing run.js via node (6 commands). From DangQuangSE/team-development-skills.

not rated 19 5d ago A tokens not measured

PostToolUse

66

gaia-research/gaia-skill-tree

Hook Claude Code

One of 2 in settings.json

Runs after a tool call finishes for Write, Edit, Edit and Write tool calls, running an inline shell check (2 commands). From gaia-research/gaia-skill-tree.

not rated 19 today A tokens not measured

UserPromptSubmit

67

narosemena/master-instructional-design

Hook Claude Code

One of 4 in settings.json

Runs when you submit a prompt, before the agent sees it, executing reference-router.py via python3. From narosemena/master-instructional-design.

not rated 18 4mo ago A tokens not measured

SessionStart

68

tractorjuice/arckit-codex

Hook

One of 6 in hooks.json

Runs when a session starts on startup, resume and clear, executing arckit-codex-hook.mjs. From tractorjuice/arckit-codex.

not rated 16 yesterday A tokens not measured

PostToolUse

69

ReadyToGo-Education/fluxo_criativo

Hook Claude Code

One of 4 in settings.json

Runs after a tool call finishes for Bash, Edit, Write, MultiEdit, Agent, Task, Write, Edit, Write, Edit, Write, Edit, MultiEdit, Write, Edit, Bash, Agent, Task, WebFetch and WebSearch tool calls, executing gsd-context-monitor.js, gsd-phase-boundary.sh, copy-review.js, painel-validar.js and agent-status-writer.js via…

not rated 15 1mo ago A tokens not measured

Stop

70

squirrelsoft-dev/dev

Hook Claude Code

One of 6 in settings.json

Runs when the agent finishes a response, executing stop-quality-gate.sh and task-summary.sh via bash (2 commands). From squirrelsoft-dev/dev.

not rated 14 20d ago A tokens not measured original MIT

SessionStart

71

ngocsangyem/MeowKit

Hook Claude Code

One of 8 in settings.json

Runs when a session starts, executing ensure-skills-venv.sh, project-context-loader.sh, dispatch.cjs, jira-env-loader.sh and capability-bootstrap.sh via bash (5 commands). From ngocsangyem/MeowKit.

not rated 14 1mo ago A tokens not measured original MIT

PreToolUse

72

ruoyu123123/ruoyuai

Hook Claude Code

One of 5 in settings.json

Runs before the agent uses a tool for Agent, Bash, Write, Edit and MultiEdit tool calls, executing pretooluse_agent_gate.py, pretooluse_step_research.py, pretooluse_subsystems_gate.py, pretooluse_plan_step_anti_skip.py and pretooluse_chapter_edit_gate.py (5 commands). From ruoyu123123/ruoyuai.

not rated 13 1mo ago A tokens not measured

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: