More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    ⚔️ Guardrail Fallback Linter

    2

    This skill acts as a specialized static analysis tool for LLM integrations, specifically designed for the "Fable 5" era of AI.

    $12

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    ⚔️ Guardrail Fallback Linter

    ⚔️ Guardrail Fallback Linter

    Example session with this skill installed

    Scan my codebase for LLM calls that might break if a guardrail blocks the response or falls back to an older model.

    • Read your context and instructions
    • Compiled the guardrail fallback linter

    [RISK] file: src/api/generate.ts:42
    Rule: unhandled-refusal
    Message: Anthropic client call lacks a 'refusal' or 'error' branch.
    Evidence: const result = await anthropic.messages.create({...});
    [!] Warning: Downstream JSON.parse(result.content) will fail on fallback refusal.

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

    About this skill

    What it does

    This skill acts as a specialized static analysis tool for LLM integrations, specifically designed for the "Fable 5" era of AI. It scans your Python or TypeScript source code to identify call sites that assume a model will always return a successful, valid response. It flags instances where code lacks 'refusal' handling or fails to account for silent fallbacks to older model versions (like Opus 4.8) when a high-risk request is blocked.

    Why use this skill

    Standard linters don't understand LLM lifecycle risks. As safety guardrails become more prevalent, your code is increasingly likely to receive a "refusal" or a response from a less-capable fallback model. If your code parses these responses blindly, it will crash or produce degraded results. This skill identifies these "blind spots" so you can implement graceful handling before they hit production.

    Supported tools

    • Languages: Python, JavaScript, TypeScript
    • Frameworks: Common LLM client patterns (OpenAI, Anthropic, LangChain)
    • Workflow: CLI-based scanning with remediation snippets provided

    The output provides a detailed report including rule IDs, severity levels, and specific lines of evidence, making it easy to integrate into your CI/CD audit process.

    Heuristic detector. It recognizes the client patterns in its config and flags likely-unhandled calls for review. It cannot confirm a fallback routes correctly or that a user sees a graceful message; those are in the manual checklist. A reliability check, not a way to bypass any safety guardrail.

    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 5 months ago

    Permissions

    Terminal / Shell
    Read Files

    File Scopes

    **/*.py
    **/*.js
    **/*.ts
    **/*.jsx
    **/*.tsx

    Read-only. Recognized call patterns and refusal signals load from an editable references/llm-call-patterns.json. It does not run your code or call a model.

    Listed5 months ago

    What's inside

    Frequently Asked Questions

    This skill scans your codebase for LLM calls that lack error handling for content refusals or silent model fallbacks, preventing runtime crashes and 'hallucinations' caused by unexpected response formats.

    The linter is optimized for Python, JavaScript, and TypeScript, natively supporting standard patterns used in the OpenAI and Anthropic SDKs as well as LangChain integrations.

    While it identifies general logic errors, it is specifically tuned to detect gaps in 'refusal' handling and hardcoded model dependencies that fail when high-risk prompts trigger safety blocks in newer models like Fable 5.

    You will receive the core scanning engine compatible with major AI agent CLI environments, along with a library of remediation snippets to help you quickly fix flagged code.

    The skill is designed for seamless integration into your existing CI/CD pipeline, allowing you to automatically audit new code commits for LLM vulnerabilities before they reach production.

    New in Code Quality & Review