hooks-permission-request-hook

name	hooks-permission-request-hook
description	Generate a PermissionRequest hook with auto-approve/deny rules. Use when needing a safer alternative to --dangerouslySkipPermissions tailored to your project stack.
args	[--strict] [--category <name>...]
allowed-tools	Read, Write, Edit, Glob, Grep, Bash, TodoWrite
argument-hint	--strict to deny unknown commands, --category git|test|lint|build|gh|deny
disable-model-invocation	true
created	"2026-03-13T00:00:00.000Z"
modified	"2026-07-18T00:00:00.000Z"
compatibility	claude-code
reviewed	"2026-04-29T00:00:00.000Z"

/hooks:permission-request-hook

Generate a PermissionRequest hook that auto-approves safe operations, auto-denies dangerous ones, and passes everything else through for user decision. A safer, project-aware alternative to --dangerouslySkipPermissions.

When to Use This Skill

Use this skill when...	Use /hooks:hooks-configuration instead when...
You want auto-approve/deny rules for Claude Code permissions	Configuring other hook types (PreToolUse, Stop, SessionStart)
Replacing --dangerouslySkipPermissions with targeted rules	Need general hooks knowledge or debugging
Setting up project-specific permission automation	Writing entirely custom hook logic from scratch
You need a test harness to validate approve/deny behavior	Understanding hook lifecycle events

Auto Mode vs PermissionRequest Hook

Auto mode (Claude Code 2.1.83+) routes most approve/deny decisions through a classifier model. It overlaps with — but does not replace — a PermissionRequest hook. Choose this skill when you need any of:

• Deterministic, auditable rules — the classifier's probabilistic answer is unsuitable for compliance contexts
• Project-specific deny lists that go beyond the default trust set
• Hard 0% false-positive guarantees for specific commands (the hook is exact, the classifier is not)
• Pre-approve narrow patterns so they skip the classifier round-trip and avoid latency/token cost

Hooks coexist with auto mode — they fire alongside the classifier. See .claude/rules/auto-mode.md for the full auto-mode model and how it interacts with allow rules and subagents.

Context

Detect project stack:

• Lockfiles: !find . -maxdepth 1 \( -name 'package-lock.json' -o -name 'yarn.lock' -o -name 'pnpm-lock.yaml' -o -name 'bun.lockb' -o -name 'poetry.lock' -o -name 'uv.lock' -o -name 'Cargo.lock' -o -name 'go.sum' -o -name 'Gemfile.lock' \)
• Project files: !find . -maxdepth 1 \( -name 'package.json' -o -name 'pyproject.toml' -o -name 'requirements.txt' -o -name 'Cargo.toml' -o -name 'go.mod' -o -name 'Gemfile' \)
• Existing settings: !find . -path '*/.claude/settings.json' -maxdepth 3 -type f