skill-llm-integration

skill-llm-integration is a cursor rule for Cursor from dewtech-technologies/dare-method. It costs 0 tokens per session (2,150 once invoked), scanned A, original, MIT.

A set of rules for connecting applications to language models such as Gemini, Claude, OpenAI, or Ollama, including a common provider interface and output checks.

In plain words
What is it for?
It is for adding reliable model-generated features with versioned prompts, time-based caching, token-bucket rate limiting, and JSON Schema validation.
Why use it?
It helps control external model calls, reuse cached results, limit request rates, reject invalid output, and defend against prompt injection.

Cursor rule for Cursor

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 rules/dewtech-technologies/dare-method/skill-llm-integration
Clone the repo
git clone --depth 1 https://github.com/dewtech-technologies/dare-method

Made for: 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.

agentmods badge for skill-llm-integration

README.md
[![agentmods](https://agentmods.dev/badge/rules/dewtech-technologies/dare-method/skill-llm-integration.svg)](https://agentmods.dev/rules/dewtech-technologies/dare-method/skill-llm-integration)
Your own site
<a href="https://agentmods.dev/rules/dewtech-technologies/dare-method/skill-llm-integration"><img src="https://agentmods.dev/badge/rules/dewtech-technologies/dare-method/skill-llm-integration.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 2,150 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00000 $0.02150
Opus 5 $0.00000 $0.01075
Sonnet 5 $0.00000 $0.00430
Haiku 4.5 $0.00000 $0.00215

Measured today against content hash a3832fe6e05d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-llm-integration 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 today.

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.

implementations/cursor/.cursor/rules/skill-llm-integration.mdc · 296 lines

How it starts

The opening of the file, as written. The whole thing — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: LLM Integration DARE

Você é um especialista em integração com LLMs. Esta skill garante que toda chamada a LLM em projeto DARE seja abstraída, cacheada, rate-limited, validada e defendida contra prompt injection.

Arquitetura recomendada

┌──────────────────────────────────────────────────────┐
│  Handler / Service de negócio                        │
└──────────────────────────────────────────────────────┘
                       ↓ injeta
┌──────────────────────────────────────────────────────┐
│  LLMProvider (interface)                             │
│  ├── GeminiProvider                                  │
│  ├── ClaudeProvider                                  │
│  ├── OpenAIProvider                                  │
│  └── OllamaProvider (local)                          │
└──────────────────────────────────────────────────────┘
                       ↓ wrap
┌──────────────────────────────────────────────────────┐
│  Cache (TTL) + RateLimit (token bucket) + Schema     │
└──────────────────────────────────────────────────────┘
                       ↓
┌──────────────────────────────────────────────────────┐
│  HTTP call externo                                   │
└──────────────────────────────────────────────────────┘

Os 5 pilares

1. LLMProvider abstraction

Nunca chame SDK direto em Handler ou Service de negócio.

// ❌ Errado
class SummaryService {
  async run(text: string) {
    const client = new GoogleGenAI({ apiKey: 'xxx' });
    return client.generateContent({ contents: text });
  }
}

// ✅ Certo
class SummaryService {
  constructor(private llm: LLMProvider) {}
  async run(text: string) {
    return this.llm.complete({
      promptId: 'summarize-v1',
      input: { text },
      schema: SummarySchema,
    });
  }
}

2. Cache em memória com TTL

Key = hash(promptId + input + model). TTL configurável (default 1h).

AP-02: sem cache = custo explode em loops + latência ruim.

3. Rate limit via token bucket

Read the full file on GitHub · 296 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. today First seen · 296 lines · 0 tokens per session scan A a3832fe6e05d

Subscribe to this mod's changes

skill-llm-integration is a cursor rule published in the GitHub repository dewtech-technologies/dare-method (5 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,150 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 2026-09-03.