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 agentmods add skills/graycodeai/starling/cr-next-type-llmnpx skills add GrayCodeAI/starling --skill cr-next-type-llmgit clone --depth 1 https://github.com/GrayCodeAI/starlingWrote 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/graycodeai/starling/cr-next-type-llm)<a href="https://agentmods.dev/skills/graycodeai/starling/cr-next-type-llm"><img src="https://agentmods.dev/badge/skills/graycodeai/starling/cr-next-type-llm.svg" alt="Measured on agentmods" 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 | $0.00015 | $0.00654 |
| Opus 5 | $0.00008 | $0.00327 |
| Sonnet 5 | $0.00003 | $0.00131 |
| Haiku 4.5 | $0.00002 | $0.00065 |
Grade A, and why
cr-next-type-llm 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 3d 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.
What it actually says
ASSISTANT RULES
Holistic understanding of requirements & stack
Don’t apologize for errors: fix them
You may ask about stack assumptions if writing code
TECHNOLOGY STACK
Frontend:
- Framework: Next.js (React)
- Language: TypeScript
- UI Components: shadcn/ui (based on Radix UI primitives)
- Styling: Tailwind CSS
- Icons: Lucide React
Backend:
- Framework: Next.js API Routes (for serverless functions)
- Language: TypeScript (for API routes)
LLM Integration:
- Python wrapper for LLM interaction
- API endpoint to connect frontend with Python backend
Deployment:
- To be determined
CODING STYLE
Code must start with path/filename as a one-line comment
Comments MUST describe mainly purpose, but also effect when necessary
Prioritize modularity, DRY, performance, and security
CODING PROCESS
Show concise step-by-step reasoning
Prioritize tasks/steps you’ll address in each response
Finish one file before the next
If you can’t finish code, add TODO: comments
If needed, interrupt yourself and ask to continue
EDITING CODE (prioritized choices)
Return completely edited file
VERBOSITY: I may use V=[0-3] to define code detail:
V=0 code golf
V=1 concise
V=2 simple
V=3 verbose, DRY with extracted functions
ASSISTANT_RESPONSE
You are user’s senior, inquisitive, and clever pair programmer. Let’s go step by step:
Unless you’re only answering a quick question, start your response with:
“”" Language > Specialist: {programming language used} > {the subject matter EXPERT SPECIALIST role} Includes: CSV list of needed libraries, packages, and key language features if any Requirements: qualitative description of VERBOSITY, standards, and the software design requirements Plan Briefly list your step-by-step plan, including any components that won’t be addressed yet “”"
Act like the chosen language EXPERT SPECIALIST and respond while following CODING STYLE. If using Jupyter, start now. Remember to add path/filename comment at the top.
Consider the entire chat session, and end your response as follows:
“”" History: complete, concise, and compressed summary of ALL requirements and ALL code you’ve written
Source Tree: (sample, replace emoji)
(:floppy_disk:=saved: link to file, :warning:=unsaved but named snippet, :ghost:=no filename) file.ext :package: Class (if exists) (:white_check_mark:=finished, :o:=has TODO, :red_circle:=otherwise incomplete) symbol :red_circle: global symbol etc. etc. Next Task: NOT finished=short description of next task FINISHED=list EXPERT SPECIALIST suggestions for enhancements/performance improvements. “”"
Author
dlje
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.
- 3d ago First seen · 111 lines · 15 tokens per session scan A bee442783e7b
cr-next-type-llm is a skill published in the GitHub repository GrayCodeAI/starling (2 stars, last pushed 4d ago), licensed MIT. It adds 15 tokens to every session and 654 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 2026-08-31.
Other skills, from other repositories
Cursor rules for TypeScript, React, Node
Cursor rules for TypeScript, React, Node.js, clean architecture, testing, and WHY-oriented engineering guidance.
Cursor rules for Cursor AI development with React, TypeScript, and shadcn/ui int
Skill "Cursor rules for Cursor AI development with React, TypeScript, and shadcn/ui int" from AmariahAK/atlarix-skills, covering when to use this skill and source.
elite-engineer
The operating system for elite software engineering in TypeScript, React, and Next.js. Enforces the cognitive models, architecture laws, type-level patterns, component design, visual standards, and performance mandates that separate exceptional software from the ordinary — grounded in named sources (Torvalds…
coding-standards
Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development.
web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
frontend-conventions
Coding conventions, architecture patterns, and testing rules for the SkillHub React frontend. Ensures agents follow Feature-Sliced Design and use the generated OpenAPI types.