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/aretw0/agents-labnpx agentmods add skills/aretw0/agents-lab/provider-model-discoveryWrote 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/aretw0/agents-lab/provider-model-discovery)<a href="https://agentmods.dev/skills/aretw0/agents-lab/provider-model-discovery"><img src="https://agentmods.dev/badge/skills/aretw0/agents-lab/provider-model-discovery.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 5.1 | $0.00060 | $0.01950 |
| Opus 5 | $0.00030 | $0.00975 |
| Sonnet 5 | $0.00012 | $0.00390 |
| Haiku 4.5 | $0.00006 | $0.00195 |
Grade A, and why
provider-model-discovery scanned grade A with 1 finding 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 7d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
const res = await fetch(url, { headers: { Authorization: `Bearer ${key}` } }); How it starts
The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Provider Model Discovery
Use esta skill quando precisar escolher modelos em um provider LLM com catálogo grande, especialmente antes de:
- adicionar um provider ao pi;
- escolher modelos para monitor/classifier;
- selecionar modelo barato/rápido, baseline, coder ou long-context;
- preparar canary protegido;
- transformar pesquisa ad hoc em runbook reproduzível.
Postura de segurança
Esta skill é report-only por padrão.
Não faça sem aprovação explícita do operador:
- chamadas de prompt/completion;
- alteração de
.pi/settings.json; - alteração de
routeModelRefs,providerBudgetsou default model/provider; - migração de monitor-provider;
- criação/uso de API key;
- paid spend;
- scheduler/loop/retry automático;
- armazenamento de segredo em chat, docs ou repo.
Permitido por padrão:
- verificar se a env var existe sem imprimir o valor;
- consultar endpoints de listagem de modelos quando forem read-only;
- fazer busca/fetch de documentação pública;
- classificar ids por família;
- escrever docs/packets report-only;
- preparar decision packet que ainda exige aprovação do operador.
Fluxo recomendado
1. Registrar escopo e provider
Defina no início:
| Campo | Exemplo |
|---|---|
| Provider | Alibaba DashScope |
| Env var esperada | DASHSCOPE_API_KEY |
| Região/base URL | https://dashscope-intl.aliyuncs.com/compatible-mode/v1 |
| Objetivo | cheap/fast classifier, coder/delegation, baseline |
| Protected boundary | sem settings/routing/monitor migration |
2. Verificar segredo sem vazar
Exemplo Node.js seguro:
node - <<'NODE'
const key = process.env.DASHSCOPE_API_KEY;
console.log(JSON.stringify({
hasKey: Boolean(key),
keyLength: key ? key.length : 0,
note: 'key value intentionally not printed'
}));
NODE
Nunca imprimir prefixo/sufixo da key.
3. Listar modelos read-only
Para providers OpenAI-compatible, a rota típica é:
GET <baseUrl>/models
Authorization: Bearer <env var value>
Para DashScope internacional:
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.
- 7d ago First seen · 259 lines · 60 tokens per session scan A 6ead909593f9
provider-model-discovery is a skill published in the GitHub repository aretw0/agents-lab (11 stars, last pushed 2mo ago), licensed MIT. It adds 60 tokens to every session and 1,950 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
neurolink-guide
Guide for using the NeuroLink SDK and CLI. Invoke when users ask how to use neurolink, integrate AI providers, add MCP tools, configure RAG, set up memory, deploy servers, or work with multimodal content. Covers SDK, CLI, providers, tools, and enterprise features.
opik-optimizer
Optimize LLM prompts, tools, and agents in Opik using standardized optimizer workflows (prompt optimization, tool optimization, and parameter tuning), dataset/metric wiring, and result interpretation.
codex-claude-worker
Translate natural-language user requests into bounded Claude Code worker tasks while Codex or ChatGPT remains the supervisor. Use when the user gives an ordinary prompt and wants Codex to clarify scope, choose a safe work boundary, generate a worker prompt, approve or defer worker execution, read run summaries and…
dspy-ruby
Build type-safe LLM applications with DSPy.rb — Ruby's programmatic prompt framework with signatures, modules, agents, and optimization. Use when implementing predictable AI features, creating LLM signatures and modules, configuring language model providers, building agent systems with tools, optimizing prompts, or…
research-axolotl
Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support.
mle-workflow
Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.