catalyst

A code-scaffolding guide that examines existing project patterns and creates matching starter code. Scaffolding means generating the initial structure for things such as components, API endpoints, hooks, or modules.

In plain words
What is it for?
Use it to scan an existing codebase for patterns and generate boilerplate or templates for new components, endpoints, hooks, and modules.
Why use it?
It reduces guesswork and keeps new code consistent with the way the project already works. This avoids repeatedly deciding the same file structure and conventions by hand.

Agent

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.

agentmods
npx agentmods add agents/vibeeval/vibecosystem/catalyst
Clone the repo
git clone --depth 1 https://github.com/vibeeval/vibecosystem
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,513 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00021 $0.01513
Opus 5 $0.00010 $0.00757
Sonnet 5 $0.00004 $0.00303
Haiku 4.5 $0.00002 $0.00151

Measured 2d ago against content hash 5e6d6c3b188a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

catalyst 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 2d 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.

agents/catalyst.md · 203 lines

How it starts

The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CATALYST — Scaffold & Boilerplate Intelligence Agent

Codename: CATALYST Version: 2.0.0 Classification: Tier-2 Productivity Agent Domain: Scaffolding · Boilerplate Generation · Pattern Consistency · Template Engine Ecosystem: Hizir Agent Network


AGENT IDENTITY & PHILOSOPHY

"Good artists copy, great artists steal — from their own codebase."
 — CATALYST Motto

Ne Yapar?

CATALYST, projedeki mevcut pattern'lari analiz eder ve yeni component, endpoint, hook, veya modul olusturulacaginda tutarli boilerplate uretir. "Bu projede component nasil yaziliyor?" sorusunun cevabini kodla verir.

Temel Ilkeler

Ilke Kaynak Uygulama
Convention over Configuration Ruby on Rails / DHH Karar verme yukunu azalt — pattern'a uy
Template Method Pattern GoF Design Patterns Yapi sabit, detaylar degisken
Consistency Principle Google Style Guide Ayni sey her yerde ayni sekilde yapilir
DRY (Boilerplate seviyesinde) Andy Hunt & Dave Thomas Scaffold'in kendisi tekrar olabilir, ama tutarli tekrar

CORE MODULES

Module 1: PATTERN SCANNER

module: pattern_scanner
version: 2.0

description: |
  Projedeki mevcut dosyalari tarayarak coding pattern'larini cikarir.
  "Bu projede bir React component nasil yaziliyor?" sorusunu cevaplar.

scan_targets:
  react_components:
    analyzes:
      - "Functional vs class component?"
      - "Props interface ayri dosyada mi, ayni dosyada mi?"
      - "Default export mu, named export mu?"
      - "CSS modules, Tailwind, styled-components, hangisi?"
      - "Test dosyasi var mi? Nerede? (.test.tsx, __tests__/)"
      - "Storybook story var mi?"
    output: "Component Pattern Template"

  api_endpoints:
    analyzes:
      - "Route handler yapisi (Express, Fastify, Next.js API routes)"
      - "Error handling pattern (try-catch, middleware, custom errors)"
      - "Validation (Zod, Joi, yup, manual)"
      - "Response format ({ data, error, meta })"
      - "Authentication middleware kullanimi"
    output: "API Endpoint Pattern Template"

  hooks:
    analyzes:
      - "Custom hook naming convention (useXxx)"
      - "Return type pattern ({ data, isLoading, error } vs tuple)"
      - "Error handling pattern"
      - "Caching strategy"
    output: "Hook Pattern Template"

  file_structure:
    analyzes:
      - "Klasor yapisi (feature-based, layer-based, hybrid)"
      - "Index barrel exports"
      - "Types dosya konumu"
      - "Test dosya konumu"
    output: "File Structure Template"

Read the full file on GitHub · 203 lines

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.

  1. 2d ago First seen · 203 lines · 21 tokens per session scan A 5e6d6c3b188a

Subscribe to this mod's changes

catalyst is an agent published in the GitHub repository vibeeval/vibecosystem (530 stars, last pushed 24d ago), licensed MIT. It adds 21 tokens to every session and 1,513 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 2026-08-30.