Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add majiang213/OpenClaw-MAS --skill cmd_hookifygit clone --depth 1 https://github.com/majiang213/OpenClaw-MASWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/majiang213/openclaw-mas/cmd_hookify)<a href="https://agentmods.dev/skills/majiang213/openclaw-mas/cmd_hookify"><img src="https://agentmods.dev/badge/skills/majiang213/openclaw-mas/cmd_hookify/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/majiang213/openclaw-mas/cmd_hookify"><img src="https://agentmods.dev/badge/skills/majiang213/openclaw-mas/cmd_hookify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00015 | $0.00950 |
| Opus 5 | $0.00008 | $0.00475 |
| Sonnet 5 | $0.00003 | $0.00190 |
| Haiku 4.5 | $0.00002 | $0.00095 |
Grade A, and why
cmd_hookify scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Path
The first argument is the project path. Before doing anything else:
- Extract the project path from the first argument
- Verify the path exists
- Work within that directory for all file operations and shell commands
Hookify
Create OpenClaw hooks to prevent unwanted agent behaviors by analyzing conversation patterns or explicit user instructions.
Usage
/skill cmd_hookify <project-path> [description of behavior to prevent]
If no description is provided, use the conversation-analyzer agent to find behaviors worth preventing from the current conversation.
Workflow
Step 1: Gather Behavior Info
- With description: parse the user's description of the unwanted behavior
- Without description: delegate to
conversation-analyzeragent to identify:- Explicit corrections the user made
- Frustrated reactions to repeated mistakes
- Reverted changes
- Repeated similar issues
Step 2: Design the Hook
For each behavior to prevent, determine:
- Event: which OpenClaw event to listen on (see event types below)
- Pattern: what to match (regex against message content, command source, etc.)
- Name: a descriptive kebab-case name
Note: Internal hooks can only warn (push messages to the user). They cannot block actions. Errors in handlers are caught and logged but don't prevent other handlers from running.
Step 3: Generate Hook Files
Create a hook directory at <project-path>/.openclaw/hooks/<hook-name>/:
HOOK.md:
---
name: <hook-name>
description: "<what this hook warns about>"
events: ["<event:action>"]
enabled: true
emoji: "🛡️"
---
handler.ts:
import type { InternalHookEvent } from "openclaw/plugin-sdk/hook-runtime";
const handler = async (event: InternalHookEvent) => {
if (event.type !== "<type>" || event.action !== "<action>") {
return;
}
const ctx = event.context as Record<string, unknown>;
const content = (ctx.content ?? ctx.commandSource ?? '') as string;
const pattern = /<regex pattern>/i;
if (pattern.test(content)) {
event.messages.push('⚠️ Warning: <description of unwanted behavior detected>');
}
};
export default handler;
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 110 lines · 15 tokens per session scan A 42648ad5a682
cmd_hookify is a skill published in the GitHub repository majiang213/OpenClaw-MAS (5 stars, last pushed 5mo ago), licensed MIT. It adds 15 tokens to every session and 950 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
system-audit
Conduct comprehensive system architecture evaluation. Assess design quality, technical debt, operational readiness, scalability. Use when auditing existing systems.
tech-debt-assessment
Measure, prioritize, and address technical debt. Classify debt by impact and effort. Build paydown roadmap. Use when evaluating system health or planning refactoring.
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior. 4-phase root cause investigation — NO fixes without understanding the problem first.
sentry
Sentry error tracking and debugging specialist.
shell-scripting
Shell scripting expert for Bash, POSIX compliance, error handling, and automation.
investigate
Systematically investigate bugs, test failures, build errors, performance issues, or unexpected behavior by cycling through characterize-isolate-hypothesize-test steps. Use when the user asks to "investigate this bug", "debug this", "figure out why this fails", "find the root cause", "why is this broken"…