llm-radar — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited llm-radar (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Preferred: Use the MCP server instead! This skill file is kept for backward compatibility. For the best experience, connect to the LLM Radar MCP server. See README.md for setup.
You have access to daily-updated information about AI models from OpenAI, Anthropic, and Google Gemini.
Use this when the user asks about:
The model data is in the data/ directory:
| File | Purpose |
|---|---|
data/models.json | Structured JSON with all model data |
data/MODELS.md | Human-readable model reference |
data/models.json for structured queries or data/MODELS.md for general questionsRead data/models.json, filter for vision capability, sort by price:
Based on today's data, the cheapest vision-capable models are: 1. Gemini 2.0 Flash ($0.10/$0.40 per 1M tokens) - best value 2. GPT-4o Mini ($0.15/$0.60) - reliable alternative 3. Claude 3.5 Haiku ($0.80/$4.00) - Anthropic's budget option
| Model | Price (in/out) | Context | Best For | |-------|----------------|---------|----------| | Claude 4 Sonnet | $3/$15 | 200K | Complex refactoring, understanding large codebases | | GPT-4o | $2.50/$10 | 128K | Quick code generation, debugging | | Claude 4 Opus | $15/$75 | 200K | Architecture decisions, code review |
Read the summary field from data/models.json and highlight recent releases.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.