Calls + amplification
Providers, models, endpoints, retries, agent loops, fan-out, regenerations, fallback cascades, and duplicate work.
Free open-source agent skill
Review production AI costs from the code outward.
Give Codex or Claude a method for tracing AI calls, checking cost controls, and identifying the production data needed for an economic decision.
03 / Download the skill
Trace each claim to code or runtime data.
The review maps providers, models, production call sites, wrappers, retries, loops, context assembly, caching, output controls, fallbacks, quality safeguards, and usage attribution.
- Exact file-and-line evidence
- Clear labels for observations, inferences, and runtime evidence
- Read-only review unless implementation is requested
- Codex and Claude-compatible package
Download the skill MIT licensed · v1.0
Review scope
Follow cost through the full call path.
Connect each model call to its workload, retries, context, quality controls, and downstream outcome. A list of SDK names cannot explain production cost.
Tokens + controls
Repeated prompts and tools, retrieved context, conversation history, output limits, caching, batching, and model configuration.
Measurement + quality
Usage capture, workload and customer attribution, latency, outcomes, evaluation sets, quality floors, rollout, fallback, and rollback.
Example prompt
$production-ai-cost-review Audit this repository for production AI cost controls and measurement gaps. Do not change any files.
Limits of a source review
Code alone cannot establish live traffic, provider charges, cache-hit rates, workload mix, quality, customer outcomes, verified savings, or migration payback. The skill identifies what is observable and specifies the runtime evidence needed next.
Use the production cost checklist