nm-abstract-hook-authoringGuide for creating Claude Code hooks with security-first design. Use for validation, logging, and policy enforcement
Install via ClawdBot CLI:
clawdbot install athola/nm-abstract-hook-authoringGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
rm -rf /Accesses system directories or attempts privilege escalation
/sys/Calls external URL not in known-safe list
https://github.com/athola/claude-night-market/tree/master/plugins/abstractAI Analysis
This skill is a documentation/guide for creating hooks with security-first design and contains no executable code. The external URL reference is to the skill's own GitHub repository, which is appropriate for attribution. The potentially concerning shell commands and system paths appear only as examples in documentation, not as active functionality.
Generated May 11, 2026
Financial services firms need to log all developer terminal commands for compliance. Hooks capture every Bash execution with timestamps and user context, ensuring auditability without developer friction.
In CI/CD environments, dangerous commands like 'rm -rf /' or 'DROP TABLE' must be blocked before execution. PreToolUse hooks inspect and reject unsafe inputs, preventing accidental infrastructure damage.
AI agents that run for hours may face context window pressure. PreCompact hooks save critical state to a file before compaction, so the agent can restore context seamlessly after resuming.
A recruitment platform uses TeammateIdle and TaskCompleted hooks to assign follow-up tasks among specialized agents (screening, scheduling, background check), reducing manual handoffs.
E-commerce sites use UserPromptSubmit hooks to inject user purchase history and preferences into each conversation, enabling personalized recommendations without over-engineering the prompt.
Offer a subscription-based security plugin that deploys pre-built hooks into enterprise Claude Code instances, blocking risky commands and enforcing compliance policies. Customers pay per seat or per audit log volume.
Consulting service that builds bespoke hooks for specific business workflows (e.g., CRM integration hooks, automated compliance logging). Revenue from project-based fees plus maintenance retainer.
Operate a marketplace where developers purchase or subscribe to pre-validated hooks (e.g., Slack notification hook, database audit hook). Platform takes a percentage of each transaction.
💬 Integration Tip
Start with JSON hooks in .claude/settings.json for quick validation, then migrate to Python SDK hooks when you need stateful logic, async operations, or multi-agent coordination.
Scored May 11, 2026
Audited Apr 17, 2026 · audit v1.0
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Use the @steipete/oracle CLI to bundle a prompt plus the right files and get a second-model review (API or browser) for debugging, refactors, design checks, or cross-validation.
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
This skill should be used ONLY when the user EXPLICITLY and UNAMBIGUOUSLY requests a Git repository commit-history analysis that produces aggregate collabora...
Spec-first, TDD, subagent-driven software development workflow. Use when: (1) building any new feature or app — triggers brainstorm → plan → subagent executi...
Best practices for Remotion - Video creation in React