Nm Hookify Writing Rules
v1.0.0Create markdown-based behavioral rules to prevent unwanted actions and block dangerous commands
⭐ 0· 17·1 current·1 all-time
by@athola
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description match the content: the SKILL.md is a rules authoring guide for Hookify, showing how to write markdown/YAML rule files that match patterns and warn or block. Nothing in the skill requests unrelated credentials, packages, or system access that would be inconsistent with authoring rules.
Instruction Scope
Instructions stay within the expected scope: creating .claude/hookify.*.local.md files, writing patterns/conditions, testing regex, and using simple management commands. The doc does show example shell commands (rm, python3) for testing and file management — appropriate for local rule authoring but assumes a shell/python are available.
Install Mechanism
No install spec and no code files — lowest-risk form. The guide does not attempt to download or install artifacts.
Credentials
The skill declares no environment variables, credentials, or config paths beyond instructing users to create files under .claude/. The examples reference typical development checks (e.g., .env, pytest) which are proportional to the stated purpose.
Persistence & Privilege
Flags show default behavior (always: false, model invocation allowed). The skill does not request permanent/always-on inclusion or change other skills' configs; it only documents local rule files that the user/agent would create.
Assessment
This is an authoring guide for local Hookify rules and appears internally consistent. Before enabling blocking rules, review patterns carefully to avoid false positives (overly broad regexes can block benign actions). Ensure you have backups and that .claude/ is writable and secured. The guide uses shell and python3 examples for testing/managing rules — verify those tools exist in your environment. Because rules can block commands, treat them as policy controls: test them in a safe environment and review any rule that runs with action: block before deploying widely.Like a lobster shell, security has layers — review code before you run it.
latestvk970tb6y4exzqfgm3d8bqr4b8n84p6xe
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🦞 Clawdis