Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Hallucinated API Detector: Catch Calls That Don't Exist

    1

    Turn AI-written Python into code that calls real functions: checks every import, attribute and keyword argument against the library you actually installed.

    $15

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    About this skill

    Your agent writes requests.get(url, retry=3), df.append(row) or OneHotEncoder(sparse=False). It looks right, it passes review, and it fails at runtime because that API does not exist in the version you have installed.

    Measured: on 21,318 references in unmodified scikit-learn, FastAPI and HTTPie code, 0 false BLOCKs (and the one BLOCK it raised was a real broken import). On 14 typical version-drift hallucinations it flagged all 14.

    API Reality Check ships a script that reads the installed package source (site-packages, .pyi stubs, node_modules .d.ts) without importing or running it, and checks your code against it:

    • Every call in the changed files: imported names, module attributes, methods, keyword arguments, positional argument counts, missing required arguments.
    • Follows **kwargs through the functions they are forwarded to, so requests.get(url, retry=3) is caught through Session.request.
    • Tells you the real API: accepts: ... with the valid keywords, did you mean: sparse_output, and --show requests.Session.get prints the installed signature with file and line.
    • Honest verdicts: BLOCK = proven absent; WARN = absent but the library is partly dynamic; unverifiable (compiled, not installed) is counted, never guessed.
    • Diff-aware: by default it checks only what changed; --diff main for a branch. Finds the project's .venv automatically, or --python <env>.
    • JS/TS: named imports from npm packages checked against their type declarations.
    Benchmark (pinned commits)ReferencesFalse BLOCKFalse WARN
    scikit-learn examples @ 1.8.014,57500
    FastAPI docs_src @ 0.136.13,3080 (1 real)0
    HTTPie cli3,43503

    Seeded hallucinations (removed in pandas 2.0, NumPy 1.24, scikit-learn 1.2-1.6, SQLAlchemy 2.0, pydantic 2, Matplotlib 3.9, plus invented keywords for requests and httpx): 10 BLOCK, 4 WARN, 0 missed.

    What it does not do: it cannot check values whose type it cannot infer (untyped dicts, generics), so some wrong calls are missed rather than guessed. Runtime-generated APIs (boto3 clients, metaclass ORMs) are mostly unverifiable. It checks that an API exists and the call shape is legal, not that the logic is right. JS/TS covers named imports only.

    Works in Claude Code, Cursor, Codex CLI, Copilot and any SKILL.md agent.

    Privacy: read-only, no network, no telemetry. It never imports or executes your code or your libraries.

    Python is checked fully; JS/TS is limited to named imports. Dynamic APIs like boto3 or Django managers are mostly unverifiable. Compiled modules require .pyi stubs.

    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 22 days ago

    Requires

    Git

    Permissions

    Terminal / Shell
    Network Access
    Environment Variables

    Allowed Hosts

    x
    Listed27 days ago
    Updated21 days ago

    What's inside

    Frequently Asked Questions

    This skill performs a real-time static analysis of your code against the actual library files installed in your environment (like site-packages or node_modules), catching hallucinated methods or deprecated arguments that LLMs often generate from outdated training data.

    It is compatible with any AI agent or workflow that can execute Python scripts. It supports Python 3.9+ environments (including Poetry, Conda, and uv) and Node.js projects through TypeScript definition (.d.ts) files.

    The tool is designed for speed; it uses a diff-based analysis engine that only scans changed or uncommitted files, ensuring your verification cycles remain fast even in large codebases.

    You receive the core validation script, documentation for environment integration, and lifetime access to updates. It also includes the 'smart suggestion' engine that provides corrections based on the physical source code on your disk.

    It can validate compiled modules as long as they provide .pyi stubs. However, it cannot resolve types from purely dynamic sources, such as dictionary keys or functions that return untyped objects.

    New in Code Quality & Review