Model Risk & Resilience Suite
A model you build on can fail you three ways. It can change underneath you, it can refuse a request, or it can vanish overnight, as Fable 5 did three days after launch. This suite covers all three: know what you depend on, survive losing it, and prove it on paper. What's inside and why: Model Inventory Auditor ($13) — the bill of materials. Every model and provider your code depends on, plus the single-provider concentration risk. You cannot manage what you cannot see. Model Resilience Linter ($12) — the code that won't survive a provider being pulled: single-provider lock-in, no failover, no timeout. The "would we survive an outage" check. Model Risk Register Generator ($12) — the continuity register a CISO asks for the morning after, built from your real dependencies, not a blank template. Model Migration Checker ($15) — the version coupling that breaks when you swap models: hardcoded ids, renamed params, token-limit assumptions. Guardrail Fallback Linter ($12) — the calls that break when a model blocks a response and silently falls back to a weaker one.
You save $15 vs buying individually.
What's included (5 skills)
Find the model-version coupling that breaks when you swap LLMs. Flags hardcoded model names and versions, deprecated or renamed parameters (the max_tokens to max_completion_tokens class of change), hardcoded token and context-window limits, response-format parsing tied to one model's output, tool-schema format coupling between providers, and hardcoded per-token cost constants. The patterns load from an editable model-rules table you update as new models ship.
Inventory every LLM model and provider your code depends on, the AI bill of materials, and flag the dependency risk. It lists each provider, model, and where it's used, then flags hardcoded model ids, single-provider dependency with no alternative, the same model referenced by different ids, model ids with no config or env indirection, and providers pinned in your manifests. Recognizes OpenAI, Anthropic, Google Gemini, and more from an editable list.
Find the LLM integration code that will not survive a provider being pulled or going down. Flags single-provider lock-in with no alternative, calls with no failover branch, missing timeouts, retries with no limit or backoff, no degraded-mode default, and hardcoded endpoints with no alternate. This is about the model going away, not the model declining.
Generate the model and vendor risk register a security lead asks for the morning after a model gets switched off. It scans your codebase for every model and provider, merges in the owner and data-residency notes you supply, and renders a register with provider, model, where it's used, fallback status, and an availability-risk rating per dependency. Markdown by default, CSV with a flag. Continuity-focused, not a compliance assessment.
Find the LLM integration code that breaks when a model blocks a response or falls back to a different model. Flags calls with no try/except or refusal branch, responses used or parsed with no guard for a blocked or empty answer, and hardcoded model ids with no fallback handling. Built for the Fable 5 era, where a high-risk call is blocked and silently falls back to Opus 4.8.