Install
$ agentstack add skill-runkids-ai-hooks-integration-ai-hooks-integration ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
AI Hooks Integration
Decision Tree
Does the target tool have a hooks API?
├── YES (Claude, Gemini CLI, Cursor, OpenCode)
│ └── Installing hooks for multiple tools at once?
│ ├── YES → Use install_all.py
│ │ └── Need cross-tool source detection?
│ │ ├── YES → --unified mode (recommended)
│ │ └── NO → --command mode (classic)
│ └── NO → Use single-tool scripts
│ ├── Claude/Gemini/Cursor → merge_hooks.py
│ └── OpenCode → install_opencode_plugin.py
└── NO (gh, aws, kubectl, docker, etc.)
└── Use install_cli_wrapper.py
Quick Commands
# Multi-tool: Unified mode (recommended)
scripts/install_all.py --unified --handler "/path/to/handler" --name my-hook
# Multi-tool: Classic mode
scripts/install_all.py --command "/path/to/hook" --name my-hook
# Single tool
scripts/merge_hooks.py --tool claude --path ~/.claude/settings.json --command ""
scripts/install_opencode_plugin.py --name my-hook --output ~/.config/opencode/plugins
# CLI without hooks API
scripts/install_cli_wrapper.py --cli gh --hook "/path/to/hook"
# Remove
scripts/remove_all.py --command "" --plugin ~/.config/opencode/plugins/my-hook.js
scripts/remove_cli_wrapper.py --cli gh
# Preview
--dry-run # Add to any command
Mode Comparison
| Mode | When to Use | Source Detection | Event Filtering | |------|-------------|------------------|-----------------| | Unified | Multiple AI tools share config files | Auto (process tree) | Yes | | Classic | Single tool or explicit routing | Manual (--source flag) | No | | CLI Wrapper | Tools without hooks API | N/A | N/A |
Tool Support
| Tool | Config | Events | Hook Types | Has Hooks API | |------|--------|--------|------------|---------------| | Claude | ~/.claude/settings.json | 17 events | command, http, prompt, agent | Yes | | Gemini CLI | ~/.gemini/settings.json | 11 events | command | Yes | | Cursor | ~/.cursor/hooks.json | 3 events | command | Yes | | OpenCode | ~/.config/opencode/plugins/*.js | 10 events | ES module | Yes (plugin) | | Gemini IDE | N/A | N/A | N/A | No | | gh, aws, etc. | N/A | N/A | N/A | No → Use wrapper |
Claude Code Events (17 total)
SessionStart, UserPromptSubmit, PreToolUse, PermissionRequest, PostToolUse, PostToolUseFailure, Notification, SubagentStart, SubagentStop, Stop, TeammateIdle, TaskCompleted, ConfigChange, WorktreeCreate, WorktreeRemove, PreCompact, SessionEnd
Gemini CLI Events (11 total)
SessionStart, SessionEnd, BeforeAgent, AfterAgent, BeforeModel, AfterModel, BeforeToolSelection, BeforeTool, AfterTool, PreCompress, Notification
References
| File | When to Read | |------|--------------| | references/tool-reference.md | Config paths, events, payload formats, templates | | references/use-cases.md | Hook patterns: security, formatting, testing, notifications | | references/unified-hook-usage.md | Cross-tool interference, source detection, debug |
Key Behaviors
- Idempotent: Duplicates skipped, safe to re-run
- Safe merge: Only adds; never overwrites existing hooks
- Debug:
HOOK_DEBUG=1enables logging
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: runkids
- Source: runkids/ai-hooks-integration
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.