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 agentmods add skills/unicomai/wanwu/using-model-endpointnpx skills add UnicomAI/wanwu --skill using-model-endpointgit clone --depth 1 https://github.com/UnicomAI/wanwuWhat 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 | $0.00040 | $0.00421 |
| Opus 5 | $0.00020 | $0.00211 |
| Sonnet 5 | $0.00008 | $0.00084 |
| Haiku 4.5 | $0.00004 | $0.00042 |
Grade A, and why
using-model-endpoint scanned grade A with 0 findings 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
You are a pure HTTP client of BASE_URL. Each registered model endpoint
gets its own inference kernel — a Python REPL whose network egress is scoped
to exactly that endpoint — reached via
compute_provider({'provider': '<slug>', 'code': '…'}) (<slug> from
list_compute, without the infer: prefix).
BASE_URLis preloaded (as a Python variable AND asos.environ["BASE_URL"]) — build request URLs from it, never hardcode hosts/ports. Call the model's native API withhttpx(preinstalled) orrequests; request shapes live in the provider's own runbook skill (the registration'sskillName).- Hosted endpoints: send
Authorization: Bearer $INFER_API_KEY(always the canonical env name when a credential is delivered; the credential's own name is usually aliased too). Local endpoints need no auth header. - Requests ride the sandbox HTTP proxy (
HTTP_PROXY/HTTPS_PROXYare set) — don't disable it (e.g.trust_env=False) or the endpoint is unreachable. - No job lifecycle here (no submit/harvest) — direct request/response only.
Managed endpoints (entries with managed: true / a location field in
list_compute): their lifecycle — daemon-owned start/stop, registration,
free_port()/register() — lives in the
managed-model-endpoints skill. Cells against them are still just
HTTP calls to BASE_URL; the daemon brings the model up on demand (a cold
start streams its progress into your cell and can take minutes).
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 First seen · 31 lines · 40 tokens per session scan A 2ee613c4530f
using-model-endpoint is a skill published in the GitHub repository UnicomAI/wanwu (2,452 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 40 tokens to every session and 421 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
data-engineering
Skill "data-engineering" from fengshao1227/ccg-workflow, covering 数据工程域 · data engineering, 域概览, 数据管道编排, 框架对比 and airflow 核心模式.
ai
AI/LLM 能力索引。Agent 开发、LLM 安全、RAG 系统。当用户提到 AI、LLM、Agent、RAG、Prompt 时路由到此。.
trulens-evaluation-workflow
Systematically evaluate your LLM application with TruLens.
vs-crawler
Crawl websites (news, blogs, papers, GitHub, product docs, RSS feeds) into a fixed-schema JSONL file, then create a dataset and a searchable application in Viking AI Search. Supports one-time crawl and scheduled recurring crawl with automatic incremental sync.
task-constructor
从 PyTorch/Triton 代码仓中提取算子实现，构建为 KernelBench 格式的标准化单文件自包含任务。 支持代码提取、AST 依赖追踪、函数内联、import 清理、格式验证和参考对比测试。 当用户需要从现有代码构建 taskcode 时使用此 Skill。.
tao-run-automl
Run container-backed AutoML / hyperparameter optimization (HPO) for NVIDIA TAO networks using AutoMLRunner. Handles algorithm selection (bayesian, hyperband, asha, bohb, llm, hybrid, autoresearch), WandB experiment tracking, job execution on any TAO SDK platform, result interpretation, and per-rec custom evaluation…