Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add agentproto/ts --skill agentproto-llm-endpointgit clone --depth 1 https://github.com/agentproto/tsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/agentproto/ts/agentproto-llm-endpoint)<a href="https://agentmods.dev/skills/agentproto/ts/agentproto-llm-endpoint"><img src="https://agentmods.dev/badge/skills/agentproto/ts/agentproto-llm-endpoint.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00077 | $0.03578 |
| Opus 5 | $0.00039 | $0.01789 |
| Sonnet 5 | $0.00015 | $0.00716 |
| Haiku 4.5 | $0.00008 | $0.00358 |
Grade A, and why
agentproto-llm-endpoint scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Proxy not running: `curl http://localhost:18090/v1/models` should return the How it starts
The opening of the file, as written. The whole thing — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to use
- "Route Claude through OpenRouter / Moonshot / Groq / ZAI / xAI"
- "Use the local LLM proxy" or "point Claude at my gated LLM endpoint"
- "Why is my model codename rejected?"
- "Claude Code vs Claude SDK with custom endpoints"
- Spawn failures: "Invalid API key", "model does not exist", empty turns
The proxy
The LLM endpoint proxy lives in projects/agentproto/ts/packages/llm-endpoint.
It exposes an Anthropic-compatible /v1/messages endpoint and maps "secret
codenames" to real provider models.
Codename → provider mapping
| Code | Provider | Real model | Claude equivalent |
|---|---|---|---|
jupiter-7 |
Moonshot | kimi-k2.7-code |
claude-opus-4-8 |
mars-6 |
Moonshot | kimi-k2.6 |
claude-3-opus |
saturn-5 |
OpenRouter | deepseek/deepseek-v4-pro |
claude-sonnet-5 |
neptune-4 |
OpenRouter | anthropic/claude-sonnet-4.6 |
claude-sonnet-4-6 |
uranus-8 |
OpenRouter | google/gemini-3.1-pro-preview |
claude-fable-5 |
mercury-9 |
OpenRouter | z-ai/glm-5.2 |
claude-3-haiku |
halley-1 |
OpenRouter | deepseek/deepseek-v4-flash |
claude-fable-4 |
orion-2 |
OpenRouter | xiaomi/mimo-v2.5 |
claude-opus-4-6 |
pegasus-3 |
OpenRouter | minimax/minimax-m3 |
claude-opus-4-9 |
lyra-4 |
OpenRouter | tencent/hy3-preview |
claude-opus-4-7 |
vega-5 |
OpenRouter | stepfun/step-3.7-flash |
claude-sonnet-4-5 |
venus-3 |
ZAI | glm-5.2 |
claude-3-5-fable |
pluto-2 |
Groq | qwen/qwen3.6-27b |
claude-haiku-4-5 |
atlas-6 |
Groq | llama-3.3-70b-versatile |
claude-3-5-sonnet |
titan-7 |
Groq | openai/gpt-oss-120b |
claude-sonnet-4-7 |
nova-1 |
xAI | grok-4.5 |
claude-opus-4-8 |
pulsar-2 |
xAI | grok-3.5 |
claude-sonnet-5 |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago Changed 2092f3dc03eb
- 7d ago First seen · 294 lines · 77 tokens per session scan A 71f01b0c277e
agentproto-llm-endpoint is a skill published in the GitHub repository agentproto/ts (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 77 tokens to every session and 3,578 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
deepeval
Use when discussing or working with DeepEval (the python AI evaluation framework).
prompt-enhancer
Transform poor or overly simple prompts with expert-level framing. Use when the user explicitly asks to improve, refine, or rewrite a prompt, or wants help framing a request for another AI system. Do NOT use for authoring, reviewing, or migrating system prompts or skills targeting a specific Claude model…
ml-llm-wiki
Use when answering questions from this machine-learning knowledge base. Triggers: questions about transformers, attention cost and efficiency, and long-context scaling; 'what do we know about attention', 'check the ML wiki'. Read-only querying of compiled knowledge; to add, update, supersede, lint, audit, or critique…
llm-prompting-guide
Prompt format rules for generative video and music models. Use when writing or reviewing a prompt for MiniMax H3 (text/image/reference-to-video with native audio) or MiniMax Music 3 (song generation from caption plus lyrics), in ComfyUI or elsewhere. Do NOT use for chat-assistant prompts, or for generative models not…
hatch3r-cli-jq
JSON processor and query language. Use when shaping JSON streams via jq-syntax filters and select expressions; invoke jq. Reads stdin and emits stdout; integrates seamlessly into shell pipelines.
ASCII Art
Generate ASCII art using pyfiglet (571 fonts), cowsay, boxes, toilet, image-to-ascii, remote APIs (asciified, ascii.co.uk), and LLM fallback. No API keys required.