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 instructions/chihebnabil/lovable-boilerplate/libgit clone --depth 1 https://github.com/chihebnabil/lovable-boilerplateWhat 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 | $0.00609 | $0.00609 |
| Opus 5 | $0.00304 | $0.00304 |
| Sonnet 5 | $0.00122 | $0.00122 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
lovable-boilerplate lib.instructions.md 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.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Utility & Service Guidelines
LIB ORGANIZATION RULES
File Structure
src/lib/
├── utils.ts # General utilities (keep existing cn function)
├── types.ts # Shared TypeScript interfaces
├── constants.ts # App-wide constants
├── validations/ # Zod schemas
│ ├── user.ts
│ ├── product.ts
│ └── common.ts
└── services/ # API service layer
├── api.ts # Base API client
├── userService.ts
└── productService.ts
Utility Functions (utils.ts)
// Keep existing cn function
export function cn(...inputs: ClassValue[]) {
return twMerge(clsx(inputs))
}
// Add other utilities
export function formatDate(date: Date | string): string {
return new Intl.DateTimeFormat('en-US').format(new Date(date))
}
export function debounce<T extends (...args: any[]) => any>(
func: T,
wait: number
): (...args: Parameters<T>) => void {
let timeout: NodeJS.Timeout
return (...args: Parameters<T>) => {
clearTimeout(timeout)
timeout = setTimeout(() => func(...args), wait)
}
}
Type Definitions (types.ts)
// Shared application types
export interface User {
id: string
email: string
name: string
avatar?: string
role: UserRole
}
export interface ApiResponse<T> {
data: T
message: string
success: boolean
}
export type UserRole = 'admin' | 'user' | 'guest'
export type Theme = 'light' | 'dark' | 'system'
Constants (constants.ts)
// Application constants
export const API_ENDPOINTS = {
USERS: '/api/users',
PRODUCTS: '/api/products',
AUTH: '/api/auth',
} as const
export const QUERY_KEYS = {
USERS: 'users',
PRODUCTS: 'products',
USER_PROFILE: 'user-profile',
} as const
export const ROUTES = {
HOME: '/',
DASHBOARD: '/dashboard',
USERS: '/users',
PROFILE: '/profile',
} as const
Validation Schemas (validations/)
// validations/common.ts
export const emailSchema = z.string().email('Invalid email')
export const phoneSchema = z.string().regex(/^\+?[\d\s-()]+$/, 'Invalid phone')
// validations/user.ts
export const userSchema = z.object({
name: z.string().min(2, 'Name too short'),
email: emailSchema,
phone: phoneSchema.optional(),
})
export type UserFormData = z.infer<typeof userSchema>
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.
- 2d ago First seen · 107 lines · 609 tokens per session scan A ce1fccf5a9a1
lovable-boilerplate lib.instructions.md is an instructions file published in the GitHub repository chihebnabil/lovable-boilerplate (65 stars, last pushed 1mo ago), licensed MIT. It adds 609 tokens to every session, about $0.0030 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.
Other instructions, from other repositories
claude-task-master CLAUDE.md
Claude Code instructions for eyaltoledano/claude-task-master, covering claude code instructions, task master ai instructions, test guidelines, test file placement and synchronous tests.
oh-my-copilot AGENTS.md
Instructions for RobinNorberg/oh-my-copilot, covering oh-my-copilot - intelligent multi-agent orchestration and setup.
oh-my-copilot CLAUDE.md
Instructions for RobinNorberg/oh-my-copilot, covering development guidelines, branch strategy, pr creation and commit convention.
DevoxxGenieIDEAPlugin GEMINI.md
Instructions for devoxx/DevoxxGenieIDEAPlugin, a project described as: DevoxxGenie is an agentic plugin for IntelliJ IDEA that uses local LLM's (Ollama, LMStudio, GPT4All, Jan and Llama.cpp) and Cloud based LLMs to help review, test, explain your project code. Latest version now also supports Spec Driven Development…
agent-rules child-process.instructions.md
Instructions for lirantal/agent-rules, covering system processes secure coding guidelines, your mission and spawning system processes.
rosetta command-versions-vs-presence.instructions.md
Instructions for tikoci/rosetta, a project described as: MCP Server with RouterOS docs + commands + products + changelogs, using SQLite-as-RAG, sourced from MikroTik.