llm-gateway-ops SKILL.md skillA
llm-gateway-ops from ninjasln-labs/agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add ninjasln-labs/agent-skills/llm-gateway-ops@v0.3.3Pins v0.3.3 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- ninjasln-labs/agent-skills
- Path
llm-gateway-ops/SKILL.md- Versions recorded
- 1
- Latest version
- v0.3.3, committed Oct 2, 2026
- Size
- 12,884 bytes
- Repository stars
- 3
- License
- none declared
Operate the standing configuration of an application's model calls: multi-provider access over openai-compatible endpoints, capability matrices, routing and fallback chains, quota and rate-limit budgets, inference cost attribution, and the seven provider-specific failure classes (rate limits, auth, bad request, content filtering, server error, timeout, response-shape drift). Use when wiring a second provider, choosing a fallback chain, capping spend or throughput, or naming which model tier…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# LLM Gateway Operations Everything about *calling models from an application and keeping those calls predictable*: which provider, which model, what happens when it fails, what it costs, and who is allowed to spend how much. This is not a book about models. > **v0.1.0 is a skeleton on purpose.** The two tables below — the capability matrix and the failure > taxonomy — are left as **shapes with placeholders**, not filled-in values. Model names, endpoints, > prices, context limits, and default timeouts change on the provider's schedule; a table filled in > today is a stale authority source within weeks. Fill a cell only from that provider's current > documentation, and record which document you used. Until then the cell stays `verify` and this > skill tells you to go read — rather than handing you a plausible-looking value. ## 中文速览（Quick Guide） - **做什么**：把应用接到多个模型 provider 上，管路由与降级链、配额限流、推理成本归因，并给每种 provider 特有失败一个可观察出口。 - **何时用**：要接第二个 provider、选主备降级链、控某条调用线的预算/吞吐，或判断某次请求实际由哪一档模型服务。 - **核心步骤**：①查能力矩阵确认目标模型是否支持你要的能力（tool call／JSON mode／流式／上下文）②定降级链并把切换留痕写进代码 ③设配额与超时，重试前先判幂等 ④按调用点归集 token 成本 ⑤失败时按分类走出口，不静默重试。 …
Read the whole file at its exact version.
How to install
mdr add ninjasln-labs/agent-skills/llm-gateway-ops@sha256:fd932c223c7e8019The line at the top of this page pins the label v0.3.3, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_czwxjorthapsupr5)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Oct 2, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (12884 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
ninjasln-labs/agent-skills · 3 stars · license none declared · pushed 2026-10-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_czwxjorthapsupr5 GET https://markdownregistry.com/api/v1/resolve?ref=ninjasln-labs/agent-skills/llm-gateway-ops GET https://markdownregistry.com/api/v1/blob/fd932c223c7e80191c5c6bb75b1ae7dac670831075c5e778b02666f63c0e362b
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.