AI Model Retirement Fixer (OpenAI, Claude, Gemini, xAI)

    1

    A hardcoded `gpt-4o`, a `claude-sonnet-4-5-20250929`, or a `gemini-2.0-flash` keeps working until the provider turns it off.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    AI Model Retirement Fixer (OpenAI, Claude, Gemini, xAI)

    Example session with this skill installed

    Scan the current directory for deprecated OpenAI and Anthropic models and fix any errors related to reasoning model parameters.

    • Read your context and instructions
    • Compiled the ai model retirement

    I have scanned the codebase and identified two critical issues: one model shutdown and one parameter rejection error for a reasoning model.

    Model Migration Audit

    FileLineCurrent ModelSeverityActionRecommendation
    src/llm/client.ts42gpt-4-0314ERRORReplacegpt-4o (Original retired 2024)
    src/agents/researcher.ts89o1-previewERRORFix ParamsRemove temperature, top_p
    package.json12@google/generative-aiINFOUpgradeMove to @google/genai

    Migration Fixes

    // src/agents/researcher.ts
    // Before:
    const response = await openai.chat.completions.create({
      model: "o1-preview",
      messages: [{ role: "user", content: prompt }],
      temperature: 1,
      top_p: 1
    });
    
    // After:
    const response = await openai.chat.completions.create({
      model: "o1-preview",
      messages: [{ role: "user", content: prompt }],
      // temperature and top_p removed: not supported by o1-preview reasoning effort
      max_completion_tokens: 5000 
    });
    

    Next steps

    1. Review the pricing differences between gpt-4-0314 and gpt-4o.
    2. Run npm install @google/genai to begin the SDK migration.
    3. Execute npm test to verify the new parameter configurations.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Model shutdowns break production code quietly. A hardcoded gpt-4o, a claude-sonnet-4-5-20250929, or a gemini-2.0-flash keeps working until the provider turns it off. Then the obvious replacement rejects max_tokens, temperature or stop.

    This skill gives your coding agent:

    • A zero-dependency Node scanner (Node 18+, nothing to install). It finds model ids in .js/.ts/.tsx/.mjs files, package.json, .env files and config, and reports file:line, severity, the official replacement and the source URL.
    • A dated data file (as of 2026-10-21) with 136 model rows across OpenAI, Anthropic, Gemini API and xAI. Each row was transcribed from the provider's official deprecation or migration page and carries source_url, as_of and a verified flag.
    • Parameter checks for the changes that commonly break a migration:
      • OpenAI: max_tokens → max_completion_tokens; Responses API input / max_output_tokens / output_text; sampling params on reasoning-effort GPT-6 models; tools in Chat Completions on GPT-6.
      • Anthropic: temperature, top_p and top_k are rejected on Claude 4.7+.
      • xAI: stop and penalty params are rejected on reasoning models; logprobs is ignored.
      • Google: the deprecated @google/generative-ai SDK.
    • A 7-step workflow: scan, confirm runtime-configured models, pick the replacement, fix params, upgrade SDKs carefully, verify, report.
    • A refresh helper that re-fetches the official pages and flags drift, plus a documented weekly re-check process.

    Tested on fixture repos for each provider: 9 automated tests, all passing.

    Honest limits:

    • It's a static scanner. Models chosen at runtime (from a database or secrets) need a human or agent to check.
    • Vertex AI, Bedrock and Azure schedules aren't covered.
    • Some older OpenAI and Gemini image/live/TTS rows aren't transcribed yet.
    • One OpenAI rule (stop / logit_bias on reasoning models) is marked unverified and reported only as a warning.
    • Dates are a snapshot. The scanner warns when its data is more than 14 days old.
    • It suggests fixes. Your agent makes the edits; nothing is rewritten automatically.

    What's included

    SKILL.md, scripts/scan.mjs, scripts/check-sources.mjs, scripts/build-data.mjs, scripts/render-table.mjs, data/retirements-2026-10-21.json (+ .md table), references/param-changes.md, references/sources.md, REFRESH.md, VERSION.md, CHANGELOG.md.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for LLM Ops.

    Partner platforms like Vertex AI, Bedrock, and Azure are out of scope. Static scanning may miss models constructed entirely via dynamic string concatenation at runtime.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 22 days ago

    Permissions

    Read Files
    Write Files
    Network Access
    Environment Variables
    Listed26 days ago
    Updated22 days ago

    What's inside

    Frequently Asked Questions

    This skill automates the detection and replacement of deprecated AI model IDs and incompatible parameters (like legacy sampling settings) in JS/TS codebases to prevent 400 errors and service outages.

    It supports Node.js 18+ environments and scans .js, .ts, .jsx, and .tsx files, specifically targeting SDKs from OpenAI, Anthropic, Google Gemini, and xAI.

    Unlike LLMs with static training data, this skill uses a frequently updated, human-verified database of provider shutdown dates to ensure migrations follow the latest official documentation.

    No, this skill is designed for direct provider SDKs; it does not currently support models hosted via enterprise platforms like Amazon Bedrock, Azure OpenAI, or Vertex AI.

    The skill scans your local environment variables and CI secret configurations to identify model IDs that are dynamically injected rather than hardcoded in the source.

    You receive the specialized scanner, the verified deprecation mapping database, and the automated migration workflows for replacing IDs and updating API response parsing.

    New in LLM Ops