Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    OpenAI Prompt Objects & Evals Shutdown Fix (Nov 30, 2026): Move pmpt_ Prompts to Code, Evals to Promptfoo

    1

    Any app that calls the Responses API with `prompt: { id: "pmpt_..." }`, or any release process gated on OpenAI Evals, breaks unless it moves first.

    $1

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    OpenAI Prompt Objects & Evals Shutdown Fix (Nov 30, 2026): Move pmpt_ Prompts to Code, Evals to Promptfoo

    OpenAI Prompt Objects & Evals Shutdown Fix (Nov 30, 2026): Move pmpt_ Prompts to Code, Evals to Promptfoo

    Example session with this skill installed

    Our support bot calls client.responses.create with prompt={"id": "pmpt_68ab12cd34ef", "version": "4"} and our onboarding route reads a prompt ID from ONBOARDING_PROMPT_ID. A release script runs client.evals.runs.create. What breaks on November 30 and can you migrate it?

    • Read your context and instructions
    • Compiled the openai prompt objects

    OpenAI Shutdown Migration Report — support-app — 2026-11-10

    Verdict

    NOT READY → READY after changes below: 5 blockers fixed, 3 model warnings scheduled.

    Inventory (from scanner, exit code 1 before / 0 after)

    IDKindLocationDeadlineStatus
    P1prompt-call + prompt-idapp/support.py:6 (pmpt_68ab12cd34ef, v4)2026-11-30migrated → prompts/support_reply.json
    P2prompt-callapp/route.ts:2 (ID from env)2026-11-30migrated → prompts/onboarding.json
    P3prompt-id-config.env.example:12026-11-30removed
    E1eval-apiscripts/run_eval.py:12026-11-30rebuilt → promptfooconfig.yaml
    M1model-id gpt-image-1.5app/route.ts:42026-12-01open: replace with gpt-image-2.6-flare or -sunburst
    M2model-id gpt-5-miniapp/support.py:122026-12-11open: official replacement gpt-5.6-terra
    M3model-id whisper-1app/support.py:152027-02-26open: gpt-transcribe or gpt-live-transcribe

    Verification

    #CheckResult
    V1No pmpt_/v1/prompts leftPASS (re-scan: 0 prompt findings)
    V2Rendered prompt = dashboard v4PASS (diff empty)
    V4Loader rejects missing/unused varsPASS ("missing variables ['issue']", "unused variables ['extra']")
    V6promptfoo echo dry runPASS (vars rendered, no {{ left)
    V7CI gate red on failing casePASS (exit 100 with failing case, 0 without)

    Open items

    M1–M3: run the promptfoo suite against each replacement model before switching production.

    promptfooconfig.yaml

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

    About this skill

    The deadline

    On November 30, 2026 OpenAI shuts down the v1/prompts API and reusable prompt objects, the Evals dashboard and API (read-only since October 31), and Agent Builder (official deprecations page, checked 2026-11-10). Any app that calls the Responses API with prompt: { id: "pmpt_..." }, or any release process gated on OpenAI Evals, breaks unless it moves first.

    What this skill does

    1. Scans the repo with a bundled, read-only, standard-library Python scanner: pmpt_ IDs in code and .env files, Responses API calls with a prompt object, v1/prompts and client.evals calls, possible Agent Builder workflow IDs, and every OpenAI model ID with a shutdown date from Dec 2026 to Feb 2027. Exit code 1 when blockers exist, so it can gate CI.
    2. Inventories each dependency with file:line, pinned version, variables and deadline.
    3. Recovers each prompt's exact published content plus the settings hidden in the prompt object (model, tools, text-format schema, reasoning, sampling) that your code never showed.
    4. Moves prompts into code as one JSON file per prompt, read by strict loaders for Python, TypeScript and PHP/Laravel that fail on missing, unused or unreplaced variables.
    5. Rebuilds evals in promptfoo using the same prompt file as the app, with a grader-by-grader mapping table (string check, text similarity, label model, score model, Python) and a free echo dry run that checks rendering without API cost.
    6. Verifies with an 8-point PASS/FAIL check (no IDs left, rendered prompt equals the dashboard version, settings carried over, CI gate proven red on a failing case) and writes OPENAI-SHUTDOWN-REPORT.md.

    Why not just prompt it yourself

    General models do not know these dates, the official replacements, or that a prompt object can silently carry tools and output schemas. The loaders and promptfoo config in this skill were run and tested on a sample repo on 2026-11-10 (promptfoo validate passed; eval exit codes observed: 100 on failure, 0 on pass).

    Cannot read your OpenAI dashboard: you (or the agent with your help) must copy each prompt's published content and grader definitions before November 30. Agent Builder workflows are detected and listed, not rebuilt. The grader-to-assertion mapping is a recommended equivalent, not an official table, so LLM-judged graders must be re-validated. Prompt IDs resolved at runtime from a database or no-code tool are not found by the scanner. Dates and replacements were checked on 2026-11-10 and can change; re-check the deprecations page after 2026-12-10.

    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 any payment.

    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 7 days ago

    Requires

    Python 3.8+ (scanner)
    Node.js for npx promptfoo
    OpenAI API key for real eval runs
    promptfoo
    Node.js

    Permissions

    Allowed Hosts

    api.openai.com (only when you run real promptfoo evals)
    registry.npmjs.org (npx promptfoo)

    File Scopes

    The
    project
    repository
    (read
    for
    scanning;
    write
    only
    migrated
    prompt
    files
    loaders
    promptfoo
    config
    and
    the
    report)

    The bundled scanner is read-only, standard-library only and makes no network calls.

    Listed7 days ago

    What's inside

    Frequently Asked Questions

    Per OpenAI's deprecations page (checked 2026-11-10): the v1/prompts API and reusable prompt objects, the Evals dashboard and API (read-only since October 31), and Agent Builder. This skill fully migrates the first two and detects the third.

    No. It finds and lists them and links OpenAI's official migration guide (Agents SDK or ChatGPT Workspace Agents). A workflow cannot be rebuilt reliably from its ID alone.

    Checked against official OpenAI and promptfoo documentation on 2026-11-10, with sources and the check date inside the skill. The skill tells the agent to re-check if it is used more than 30 days later.

    Model-ID scanners do not touch prompt objects or Evals. This skill handles the prompt content and hidden settings, gives tested loaders for Python, TypeScript and PHP, rebuilds evals in promptfoo from the same prompt file, and proves the CI gate fails on a broken case.

    Yes. It includes a strict PromptLoader class for PHP 8.1+ that works with Laravel's HTTP client or any OpenAI PHP SDK.

    New in LLM Ops