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 oneworks-ai/app --skill oneworks-model-servicesgit clone --depth 1 https://github.com/oneworks-ai/appWrote 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/oneworks-ai/app/oneworks-model-services)<a href="https://agentmods.dev/skills/oneworks-ai/app/oneworks-model-services"><img src="https://agentmods.dev/badge/skills/oneworks-ai/app/oneworks-model-services/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/oneworks-ai/app/oneworks-model-services"><img src="https://agentmods.dev/badge/skills/oneworks-ai/app/oneworks-model-services.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00037 | $0.03530 |
| Opus 5.5 | $0.00015 | $0.01412 |
| Sonnet 5.5 | $0.00007 | $0.00706 |
| Haiku 4.5 | $0.00004 | $0.00353 |
Grade A, and why
oneworks-model-services 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use this skill when a user wants to add, update, or troubleshoot OneWorks modelServices.
Writeback Rules
- Put account-level API keys and secrets in global config by default.
- Use project or user config only when the user explicitly asks for an override.
- Do not copy values from merged config back into a source file unless you know the target source.
- Never show API keys, secrets, tokens, or passwords in the final answer.
- If the selected provider is known, prefer built-in defaults for
provider,homepageUrl,apiBaseUrl, models, icons, and management capabilities. Only write override fields when the user asks for an override.
Config Shape
Use modelServices.<serviceKey> with these common fields:
provider: built-in provider id.title: display name.description: short display description.apiKey: service API key or secret.apiBaseUrl: only needed for custom services or explicit overrides.models: only needed for custom services or explicit overrides.billing: optional metadata for billing kind, key kind, quota unit, quota windows, and allowed use.codingPlan: optional metadata for plan links, protocol base URLs, regions, default models, and restrictions.homepageUrl: only needed to override the provider portal.management.enabled: enables model/balance/status/secret helper actions when available.management.apiKey: optional separate management API key; otherwise reuseapiKeywhen supported.
Coding Plan and Token Plan Rules
Here "Coding Plan" means a provider billing/quota product, not OneWorks or agent Plan Mode.
- Do not mix plan keys and ordinary pay-as-you-go API keys. A Coding Plan or Token Plan normally needs its dedicated key and dedicated base URL.
- Prefer built-in plan provider ids instead of overriding ordinary API providers:
kimi-code: Kimi Code, OpenAIhttps://api.kimi.com/coding/v1, Anthropichttps://api.kimi.com/coding/, modelkimi-for-coding, Kimi Code API key from the Kimi Code console. Models and quota can be queried through the dedicated/coding/v1API; do not use Moonshot/Kimi Platform PAYG balance endpoints for it.minimax-token-plan: MiniMax Token Plan, OpenAIhttps://api.minimax.io/v1, Anthropichttps://api.minimax.io/anthropic, China Anthropichttps://api.minimaxi.com/anthropic, modelMiniMax-M3, Subscription Key.qwen-coding-plan: Alibaba Cloud Model Studio Coding Plan, OpenAIhttps://coding.dashscope.aliyuncs.com/v1, Anthropichttps://coding.dashscope.aliyuncs.com/apps/anthropic, international OpenAIhttps://coding-intl.dashscope.aliyuncs.com/v1, international Anthropichttps://coding-intl.dashscope.aliyuncs.com/apps/anthropic, plan key commonlysk-sp-*.zhipu-coding-plan: Zhipu GLM Coding Plan, OpenAIhttps://open.bigmodel.cn/api/coding/paas/v4, Anthropichttps://open.bigmodel.cn/api/anthropic, modelGLM-5.2.tencent-tokenhub-coding-plan: Tencent Cloud TokenHub Coding Plan, OpenAIhttps://api.lkeap.cloud.tencent.com/coding/v3, Anthropichttps://api.lkeap.cloud.tencent.com/coding/anthropic.volcengine-ark-coding-plan: Volcengine Ark Coding Plan, OpenAIhttps://ark.cn-beijing.volces.com/api/coding/v3, Anthropichttps://ark.cn-beijing.volces.com/api/coding.baidu-qianfan-coding-plan: Baidu Qianfan Coding Plan, OpenAIhttps://qianfan.baidubce.com/v2/coding, Anthropichttps://qianfan.baidubce.com/anthropic/coding.
- OpenAI Codex and Anthropic Claude Code subscriptions are product-login entitlements, not model service API keys. ChatGPT/Codex and
claude logincan use subscription quotas, while OpenAI/Anthropic API keys still bill as ordinary API usage. - Many plan quotas are request-window based, such as 5-hour, weekly, or monthly request limits. Do not describe them as ordinary token quotas unless the provider calls the product a Token Plan.
- Many providers restrict plans to interactive coding tools and disallow backend batch jobs, automation scripts, or generic API load. Preserve
billing.allowedUse: coding_tools_onlyand show the restriction to the user. - Plan model lists are catalog defaults and may not be available from
/v1/models. Leavemodelsempty to use the built-in catalog, or writemodelsonly when the user explicitly wants an allowlist override. - DeepSeek is currently a pay-as-you-go API provider with coding-agent integrations, not a dedicated Coding Plan provider in this registry.
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.
- 1mo ago First seen · 105 lines · 37 tokens per session scan A ccafa36b2283
oneworks-model-services is a skill published in the GitHub repository oneworks-ai/app (20 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 3,530 once invoked, about $0.0001 per session on Opus 5.5. 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
ultralytics-platform
This skill should be used when user asks to "upload my model to Ultralytics Platform", "push this run to the platform", "upload a dataset to platform", "download a dataset from platform", "search platform datasets", "start cloud training", "train on platform GPUs", "export a model on platform", "deploy a model…
yolo-training
This skill should be used when user asks to "improve my mAP", "why is my model overfitting", "my training is diverging", "read my results.csv", "interpret my training curves", "my AP50 is good but AP50-95 is bad", "my recall is low", "how do I pick learning rate", "which augmentations should I use", "should I use a…
mongodb-atlas-stream-processing
Manages MongoDB Atlas Stream Processing (ASP) workflows. Handles workspace provisioning, data source/sink connections, processor lifecycle operations, debugging diagnostics, and tier sizing. Supports Kafka, Atlas clusters, S3, HTTPS, and Lambda integrations for streaming data workloads and event processing. NOT for…
mongodb-search-and-ai
Covers everything about search in MongoDB: Atlas Search (full-text), Vector Search (semantic), and Hybrid Search. Use this skill for ANY question about MongoDB search, including open-ended and explanatory ones asked before the user has any data or use case — 'how does search work in MongoDB?', 'I'm new to MongoDB…
neo4j-document-import-skill
Ingests unstructured and semi-structured documents into Neo4j as a knowledge graph. Use when chunking PDFs, HTML, plain text, or Markdown; extracting entities and relationships from text with an LLM (SimpleKGPipeline, neo4j-graphrag); loading JSON via apoc.load.json; building Document→Chunk→Entity graph structures; or…
neo4j-vector-index-skill
Create and manage Neo4j vector indexes, run vector similarity search (ANN/kNN), store embeddings on nodes or relationships, use SEARCH clause (Neo4j 2026.01+, preferred) or db.index.vector.queryNodes() procedure (deprecated 2026.04, still works on 2025.x), configure HNSW and quantization options, pick similarity…