ai-agents hooks

1,222 tagged ai-agents, measured the same way as everything else here.

Browse within: claude-code-plugin 317ai-coding 150agent-memory 132agent-orchestration 117agentic-coding 94Multi-Agent 68ai-memory 67codex-cli 66Autonomous Agents 53ai-tools 53coding-agents 50agent-framework 48agentic-workflow 48context-engineering 48

PostToolUse

73

zoharbabin/due-diligence-agents

Hook Claude Code

One of 3 in settings.json

Runs after a tool call finishes for Edit and Write tool calls, executing post-edit-lint.sh via bash. From zoharbabin/due-diligence-agents.

not rated 98 +2 28d ago A tokens not measured original Apache-2.0

PostToolUse

74

litefuse/litefuse

Hook Claude Code

One of 3 in settings.json

Runs after a tool call finishes for Edit, MultiEdit and Write tool calls, executing post-tool-use-tracker.sh. From litefuse/litefuse.

not rated 95 +2 2d ago A tokens not measured

PreToolUse

75

optave/ops-codegraph-tool

Hook Claude Code

One of 3 in settings.json

Runs before the agent uses a tool for Bash, Read and Grep tool calls, executing snapshot-pre-bash.sh, check-readme.sh, guard-git.sh, guard-pr-body.sh, commitlint-local.sh, pre-commit.sh, lint-staged.sh and enrich-context.sh with --show-toplevel (9 commands). From optave/ops-codegraph-tool.

not rated 93 +1 today A tokens not measured original Apache-2.0

PostToolUse

76

craigjmidwinter/getvect

Hook Claude Code

One of 7 in settings.json

Runs after a tool call finishes for Edit and Write tool calls, running katra agent-hook post-tool. From craigjmidwinter/getvect.

not rated 90 +1 9d ago A tokens not measured original MIT

PostToolUse

77

vstorm-co/memv

Hook Claude Code

One of 3 in settings.json

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

not rated 89 4d ago A tokens not measured original MIT

SessionStart

78

FareedKhan-dev/claude-code-staff-engineer

Hook Claude Code

Runs when a session starts on startup, clear and compact, executing run-hook.cmd. From FareedKhan-dev/claude-code-staff-engineer.

not rated 88 4mo ago A tokens not measured original MIT

SessionStart

79

zby/commonplace

Hook Claude Code

One of 2 in settings.json

Runs when a session starts on startup and resume, executing cloud-session-setup.sh. From zby/commonplace.

not rated 88 yesterday A tokens not measured CC-BY-4.0

PostToolUse

80

Tako-Research/TakoVM

Hook Claude Code

One of 2 in settings.json

Runs after a tool call finishes for Edit and Write tool calls, executing lint.sh. From Tako-Research/TakoVM.

not rated 87 4d ago A tokens not measured original Apache-2.0

BeforeTool

81

Jamkris/everything-gemini-code

Hook Claude Code

One of 6 in hooks.json

Runs on the BeforeTool event for tool == "run_shell_command", tool == "run_shell_command", tool == "run_shell_command" && tool_input.command matches "^\\s*(npm (install, test, i, ci), pnpm (install, test, i), yarn (install, test, add, remove, upgrade), bun (install, test, i, add, remove), cargo build, make, docker…

not rated 87 3mo ago A tokens not measured original MIT

PreToolUse

82

duongthinh03/portfolio

Hook Claude Code

One of 2 in settings.json

Runs before the agent uses a tool for Bash, Glob, Grep, Read, Edit and Write tool calls, executing scout-block.js via node. From duongthinh03/portfolio.

not rated 85 2mo ago A tokens not measured

PostToolUse

83

hoangsonww/AI-Agents-Orchestrator

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 hoangsonww/AI-Agents-Orchestrator.

not rated 84 +1 20d ago A tokens not measured original MIT

PreCompact

84

shyftlabs/continuum

Hook Claude Code

One of 11 in settings.json

Runs before the context is compacted for manual and auto tool calls, executing hook-handler.cjs via sh (4 commands). From shyftlabs/continuum.

not rated 84 2d ago A tokens not measured original Apache-2.0

UserPromptSubmit

85

sysnet4admin/_Book_Claude-Code

Hook Claude Code

One of 2 in settings.json

Runs when you submit a prompt, before the agent sees it, running date >> last_prompting_history.log. From sysnet4admin/_Book_Claude-Code.

not rated 81 5mo ago A tokens not measured

PostToolUse

86

alfadur7/llm-wiki-newsroom

Hook Claude Code

One of 3 in settings.json

Runs after a tool call finishes for Bash, PowerShell, Write and Edit tool calls, executing lint-chain-guard.sh and dispatch.sh via bash (2 commands). From alfadur7/llm-wiki-newsroom.

not rated 81 4d ago A tokens not measured copy · 42% MIT

PreToolUse

87

JKHeadley/instar

Hook Claude Code

One of 14 in settings.json

Runs before the agent uses a tool for AskUserQuestion, mcp__.*, Write, Edit and MultiEdit tool calls, executing free-text-guard.sh, external-operation-gate.js and duplicate-build-start-gate.js via bash (3 commands). From JKHeadley/instar.

not rated 77 2d ago A tokens not measured original MIT

PreToolUse

88

mukul975/Threatswarm

Hook Claude Code

One of 4 in settings.json

Runs before the agent uses a tool for Bash tool calls, executing scope_check.py via python3. From mukul975/Threatswarm.

not rated 77 4mo ago A tokens not measured original MIT

PreToolUse

89

TOKTOKHAN-DEV/agent-company

Hook Claude Code

One of 3 in settings.json

Runs before the agent uses a tool for Bash tool calls, executing guard-image-generation.sh via bash. From TOKTOKHAN-DEV/agent-company.

not rated 75 +1 10d ago A tokens not measured original MIT

TaskCompleted

90

vanillagreencom/kendex

Hook Claude Code

One of 6 in settings.json

Runs when a task is marked completed, executing task-completed-check.sh via bash. From vanillagreencom/kendex.

not rated 74 +9 changed today A tokens not measured original MIT

SessionStart

91

superplan-md/superplan-plugin

Hook Claude Code

Runs when a session starts on startup, clear and compact, executing run-hook.cmd. From superplan-md/superplan-plugin.

not rated 72 4mo ago A tokens not measured original Apache-2.0

PreToolUse

92

bahdotsh/indxr

Hook Claude Code

One of 2 in settings.json

Runs before the agent uses a tool for Read and Bash tool calls, running an inline shell check (2 commands). From bahdotsh/indxr.

not rated 72 5mo ago A tokens not measured original MIT

PostToolUse

93

willdady/platypus

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 willdady/platypus.

not rated 72 +3 yesterday A tokens not measured original MIT

SessionStart

94

edutrul/drupal-ai

Hook Claude Code

One of 2 in settings.json

Runs when a session starts on startup, resume, clear and compact, executing session-start.sh and session-resume.sh (2 commands). From edutrul/drupal-ai.

not rated 71 3mo ago A tokens not measured original MIT

PreToolUse

95

nylas/cli

Hook Claude Code

One of 3 in settings.json

Runs before the agent uses a tool for Bash and Write tool calls, executing file-size-check.sh with --cached and --name-only (3 commands). From nylas/cli.

not rated 68 18d ago A tokens not measured original MIT

PreToolUse

96

stuinfla/ruvnet-brain

Hook Claude Code

One of 2 in settings.json

Runs before the agent uses a tool for Bash tool calls, executing version-bump-gate.sh. From stuinfla/ruvnet-brain.

not rated 65 yesterday 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: