More screenshots
Works with the AI tools you already use
⚔️ Guardrail Fallback Linter
This skill acts as a specialized static analysis tool for LLM integrations, specifically designed for the "Fable 5" era of AI.
Secure checkout via Stripe
See it in action
You say
Scan my codebase for LLM calls that might break if a guardrail blocks the response or falls back to an older model.
Your agent does
[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.
What you get
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.
How to install
Drop the file into your AI Agent. Works with Claude, Cursor, ChatGPT, and 20+ more.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
30-day refund
Not a fit? Get your money back
Trust & safety
Security scanned
Verified clean 1 month ago
- 30-day refund guarantee
- One-time purchase, yours forever
- Secure checkout via Stripe
Creator
JustHandled Labs builds focused agent skills for the work nobody wants to do by hand. Each one is a single repeatable job done well: catching the security and data mistakes that quietly ship, keeping docs and tests honest, gating the commands an agent is about to run, sharpening writing, and handling the founder chores around launches, outreach, and brand setup. Not generic AI productivity. Specific workflows that are easy to run, review, and repeat. Maintained by H.J. Westerfield, with a background in communications, editing, project coordination, customer support, and practical AI systems. Tools for people who want useful automation without theatrical complexity.
Also available in a bundle
Frequently Asked Questions
Popular in Code Review
🧪 AI Build Sanity Check
Check an AI-built app for work that looks finished but is not: leftover TODOs and stubs, fake or mock data returned as real, errors quietly swallowed, placeholder content, and endpoints that fake success. Read-only, every finding explained in plain English for non-coders.
complexity-quality-gate-enforcer
Teaches AI coding agents to enforce hard numeric quality thresholds on code complexity — cyclomatic complexity, cognitive complexity, coupling, and maintainability index — as deterministic CI/CD gates
codegraph-ast-grep
Supercharge repo exploration and refactoring with semantic call-graph tracing and structural AST pattern matching.
typescript-type-auditor
Deep audit of TypeScript codebases for type safety violations, unsafe casts, and runtime-risk anti-patterns.