free-ai-gateway: Skill for Claude Code

.agents/skills/provider-scaffolding/SKILL.md

provider-scaffolding is a skill for Claude Code, Codex from zaber-dev/free-ai-gateway. It costs 25 tokens per session (538 once invoked), scanned A, original, MIT.

A step-by-step guide for adding a new AI service provider to the core of an AI gateway. It covers the adapter code, settings, authentication, and response format needed to connect the provider.

In plain words
What is it for?
Use it when implementing a provider adapter in @free-ai-gateway/core, including API-key handling, requests to the provider, model selection, errors, and returned data.
Why use it?
It removes the guesswork from connecting another AI service to an existing gateway. It also helps keep new provider connections consistent with the gateway's shared interface.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is zaber-dev/free-ai-gateway's own configuration. It tells Claude Code and Codex how to work on free-ai-gateway itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything free-ai-gateway configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import { ProviderModel, UnifiedRequest, UnifiedResponse } from "../types/contracts";.

Reuse

Borrowing it

Nothing to install: this file belongs to zaber-dev/free-ai-gateway. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/zaber-dev/free-ai-gateway/main/.agents/skills/provider-scaffolding/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/zaber-dev/free-ai-gateway

Made for: Claude Code, Codex.

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 provider-scaffolding

README.md
[![agentmods](https://agentmods.dev/badge/skills/zaber-dev/free-ai-gateway/provider-scaffolding/github.svg)](https://agentmods.dev/skills/zaber-dev/free-ai-gateway/provider-scaffolding)
Your own site
<a href="https://agentmods.dev/skills/zaber-dev/free-ai-gateway/provider-scaffolding"><img src="https://agentmods.dev/badge/skills/zaber-dev/free-ai-gateway/provider-scaffolding/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for provider-scaffolding

Your own site · 80×15
<a href="https://agentmods.dev/skills/zaber-dev/free-ai-gateway/provider-scaffolding"><img src="https://agentmods.dev/badge/skills/zaber-dev/free-ai-gateway/provider-scaffolding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 538 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Data Exfiltration · line 60
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
How audits are shown
Origin original 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 5.1 $0.00025 $0.00538
Opus 5 $0.00013 $0.00269
Sonnet 5 $0.00005 $0.00108
Haiku 4.5 $0.00003 $0.00054

Measured 11d ago against content hash d813c1caa3e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

provider-scaffolding 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 11d 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.

.agents/skills/provider-scaffolding/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Provider Scaffolding Skill

Use this skill whenever an agent needs to add a new AI provider adapter into @free-ai-gateway/core.

Step-by-Step Scaffolding Procedure

1. Create Adapter Class

In packages/core/src/providers/<provider-id>.ts:

import { BaseProvider } from "./base-provider";
import { ProviderModel, UnifiedRequest, UnifiedResponse } from "../types/contracts";
import { ProviderError } from "../errors/errors";

export class NewProviderAdapter extends BaseProvider {
  public static readonly providerId = "new_provider";

  async invoke(request: UnifiedRequest, model: ProviderModel): Promise<UnifiedResponse> {
    const apiKey = this.getApiKey("NEW_PROVIDER_API_KEY");
    if (!apiKey) {
      throw new ProviderError("Missing NEW_PROVIDER_API_KEY", 401);
    }

    const { data } = await this.post(
      "chat/completions",
      {
        ...request.payload,
        model: model.id,
      },
      {
        headers: {
          Authorization: `Bearer ${apiKey}`,
        },
      }
    );

    return {
      servedBy: {
        provider: this.config.id,
        model: model.id,
      },
      data,
    };
  }
}

2. Add Configuration to packages/core/src/config/providers.json

{
  "id": "new_provider",
  "name": "New Provider",
  "auth": "api_key",
  "base_url": "https://api.newprovider.ai/v1",
  "limit_scope": "account",
  "openai_compatible": true,
  "confidence": "official",
  "models": [
    {
      "id": "model-v1",
      "capabilities": ["text", "tool_calling"],
      "limits": {
        "rpm": 60,
        "rpd": 1000
      }
    }
  ]
}

3. Export in packages/core/src/providers/index.ts & packages/core/src/index.ts

Export the class so ProviderLoader and downstream packages can consume it:

// in packages/core/src/providers/index.ts
export { NewProviderAdapter } from "./new-provider";

// in packages/core/src/index.ts
export { NewProviderAdapter } from "./providers";

4. Verify with Tests

npm test --workspace=@free-ai-gateway/core

Read the full file on GitHub · 92 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. 11d ago First seen · 92 lines · 25 tokens per session scan A d813c1caa3e7

Subscribe to this mod's changes

provider-scaffolding is a skill published in the GitHub repository zaber-dev/free-ai-gateway (14 stars, last pushed 4d ago), licensed MIT. It adds 25 tokens to every session and 538 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 2026-08-30.