Ai Litellm Gateway Cost Control
Use when reviewing model gateway routing, provider fallback, budget limits, rate limits, or agent cost controls.
Install
$ agentstack add skill-aidi1723-safe-agent-skills-ai-litellm-gateway-cost-control ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
AI LiteLLM Gateway Cost Control
When To Use
Use this skill when an agent or product routes requests across multiple model providers and needs cost, latency, logging, rate, or fallback policy review.
Safe Workflow
- Identify providers, model names, routing rules, budget owner, and fallback
order.
- Separate reliability fallback from cost optimization and compliance routing.
- Define per-task, per-user, and per-workspace limits before production use.
- Record what happens when a provider fails, slows down, or exceeds budget.
- Keep credentials and provider secrets outside skill instructions.
- Verify that logs do not expose private prompts, user data, or credentials.
Expected Output
- routing policy summary
- budget and rate limit plan
- provider fallback matrix
- logging and privacy notes
- residual risk list
Verifier Expectations
- provider list check
- budget limit check
- private data logging check
- fallback behavior check
Failure Handling
If license or provider policy is unclear, keep the skill in review state and avoid recommending default production use.
Boundary
This is a reference skill inspired by LiteLLM. It documents gateway review patterns and does not bundle proxy code, provider connectors, or credentials.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: aidi1723
- Source: aidi1723/safe-agent-skills
- License: Apache-2.0
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.