gateway: Skill for Claude Code

.claude/skills/review-provider/SKILL.md

review-provider is a skill for Claude Code from adaline/gateway. It costs 14 tokens per session (205 once invoked), scanned A, original, MIT.

A checklist for reviewing an AI provider integration against the repository’s expected structure and a reference OpenAI implementation. It checks folders, validation schemas, error mapping, dependencies, build output, and exports.

In plain words
What is it for?
Use it to review a provider package, compare it with the OpenAI provider, find missing files or incorrect types, verify workspace dependencies, and report build or export issues.
Why use it?
It makes structural and compatibility problems easier to spot before an integration is accepted or used. The input does not describe automatic code changes, so it should be treated as a review and reporting aid.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

This is adaline/gateway's own configuration. It tells Claude Code how to work on 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 gateway configures →

Reuse

Borrowing it

Nothing to install: this file belongs to adaline/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/adaline/gateway/main/.claude/skills/review-provider/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/adaline/gateway

Made for: Claude Code.

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 review-provider

README.md
[![agentmods](https://agentmods.dev/badge/skills/adaline/gateway/review-provider/github.svg)](https://agentmods.dev/skills/adaline/gateway/review-provider)
Your own site
<a href="https://agentmods.dev/skills/adaline/gateway/review-provider"><img src="https://agentmods.dev/badge/skills/adaline/gateway/review-provider/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 review-provider

Your own site · 80×15
<a href="https://agentmods.dev/skills/adaline/gateway/review-provider"><img src="https://agentmods.dev/badge/skills/adaline/gateway/review-provider.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 205 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 pass 7 Sept 2026
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 $0.00014 $0.00205
Opus 5 $0.00007 $0.00102
Sonnet 5 $0.00003 $0.00041
Haiku 4.5 $0.00001 $0.00020

Measured 9d ago against content hash 068ff0edbd2d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

review-provider 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 9d 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.

.claude/skills/review-provider/SKILL.md · 18 lines

What it actually says

Review the provider at core/providers/$ARGUMENTS/ for:

  1. Structure compliance: Verify it has src/configs/, src/models/, src/provider/ directories
  2. Type safety: Check all Zod schemas are properly defined and exported
  3. Error handling: Verify provider errors are mapped to GatewayError subclasses
  4. Package.json: Check @adaline/types and @adaline/provider are workspace:* dependencies
  5. Build: Verify tsup.config.ts produces ESM + CJS + types output
  6. Exports: Check the package exports from src/index.ts correctly

Compare with core/providers/openai/ as the reference implementation and report any deviations or issues.

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. 9d ago First seen · 18 lines · 14 tokens per session scan A 068ff0edbd2d

Subscribe to this mod's changes

review-provider is a skill published in the GitHub repository adaline/gateway (606 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 205 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.