What is hook-development?

A set of rules for developing TypeScript hooks, which are small programs that run before or after an agent uses a tool or when a session ends.

Use it when building hooks that validate tool calls, change their parameters, format results, inject context, or allow and deny actions.

It gives hook code consistent input, output, error handling, speed, and build requirements.

hook-development — Cursor rule for Claude Code and Cursor by vibeeval

Install

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.

Clone the repo

git clone --depth 1 https://github.com/vibeeval/vibecosystem

Made for: Claude Code, Cursor.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/rules/vibeeval/vibecosystem/hook-development/github.svg)](https://agentmods.dev/rules/vibeeval/vibecosystem/hook-development)

Your own site

<a href="https://agentmods.dev/rules/vibeeval/vibecosystem/hook-development"><img src="https://agentmods.dev/badge/rules/vibeeval/vibecosystem/hook-development/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.

Your own site · 80×15

<a href="https://agentmods.dev/rules/vibeeval/vibecosystem/hook-development"><img src="https://agentmods.dev/badge/rules/vibeeval/vibecosystem/hook-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Nothing until a file matches its globs; then the whole rule loads.

When invoked 265 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00000	$0.00265
Opus 5.5	$0.00000	$0.00106
Sonnet 5.5	$0.00000	$0.00053
Haiku 4.5	$0.00000	$0.00026

Measured 1mo ago against content hash 6a514aac660f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hook-development 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 1mo 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.

.cursor/rules/hook-development.mdc · 41 lines

What it actually says

Hook Development Rules

Hook Types

PreToolUse: Runs before a tool executes (validation, parameter modification)
PostToolUse: Runs after a tool executes (formatting, checking)
Stop: Runs when session ends (final validation)

File Structure

hooks/
  src/           # TypeScript source files
    shared/      # Shared utilities
  dist/          # Compiled .mjs files (esbuild output)
  package.json
  tsconfig.json

Hook Output Format

interface HookResult {
  result: string;           // shown in terminal
  systemMessage?: string;   // injected into AI context
  permissionDecision?: "allow" | "deny";
  reason?: string;          // if denied
}

Rules

Always handle errors with try/catch
Return valid JSON to stdout
Read input from stdin (JSON)
Use systemMessage for AI context injection, not message
Keep hooks fast (< 500ms)
Build with: cd hooks && npm run build

Changes

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.

1mo ago First seen · 41 lines · 0 tokens per session scan A 6a514aac660f

Subscribe to this mod's changes

hook-development is a cursor rule published in the GitHub repository vibeeval/vibecosystem (536 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 265 tokens. 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 2026-08-30.

Building agents Claude Code ai-agents ai-software-team anthropic automation claude

facebook-ads

Meta Ads (Facebook & Instagram) platform expertise. Audit campaigns, audiences, creative strategy, pixel tracking, and CAPI. Use when the user asks about Facebook Ads, Instagram Ads, Meta Ads, social media advertising, Advantage+ campaigns, or Meta pixel/CAPI setup.

thatrebeccarae/claude-marketing · 55 tokens

supreme-content-craft

Principal content craft for SEO/SEM/Header Binding/Copywriting/Marketing/Writing with six persuasion frameworks (AIDA, Cialdini, StoryBrand/PAS/FAB/Schwartz/SUCCESs/Ogilvy/Hopkins, Schopenhauer ethical eristic, Joe Girard Law of 250, Cialdini Pre-Suasion), Features to Project to How to Benefits to Sales to Purchase…

davccavalcante/supreme-coding-guidelines-skill.ah · 102 tokens

hook-development