Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/vibeeval/vibecosystemnpx agentmods add agents/vibeeval/vibecosystem/catalystWrote 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/agents/vibeeval/vibecosystem/catalyst)<a href="https://agentmods.dev/agents/vibeeval/vibecosystem/catalyst"><img src="https://agentmods.dev/badge/agents/vibeeval/vibecosystem/catalyst/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/agents/vibeeval/vibecosystem/catalyst"><img src="https://agentmods.dev/badge/agents/vibeeval/vibecosystem/catalyst.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 | $0.00021 | $0.01513 |
| Opus 5.5 | $0.00008 | $0.00605 |
| Sonnet 5.5 | $0.00004 | $0.00303 |
| Haiku 4.5 | $0.00002 | $0.00151 |
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 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.
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"
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 · 203 lines · 21 tokens per session scan A 5e6d6c3b188a
catalyst is an agent published in the GitHub repository vibeeval/vibecosystem (536 stars, last pushed 2mo ago), licensed MIT. It adds 21 tokens to every session and 1,513 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other agents, from other repositories
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
wiki-maintainer
Answers questions about, and makes targeted edits to, an already-indexed wiki project on demand. Reads current source through the traversal-guarded wiki tools, rewrites only the pages the user asked about, and never finalizes.
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
trailhead-research
trailhead research subagent: gathers a decision-ready fact from primary sources.
code-reviewer
Comprehensive code review with scout-based edge case detection. Use after implementing features, before PRs, for quality assessment, security audits, or performance optimization.
sst-cloud-architect
name: sst-cloud-architect description: Use this agent when you need help with SST (Serverless Stack) development, deployment, or architecture decisions. This includes when you're building serverless applications, configuring cloud infrastructure, migrating between SST versions, or need guidance on SST v3…