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 lebsral/DSPy-Programming-not-prompting-LMs-skills --skill dspy-vllmgit clone --depth 1 https://github.com/lebsral/DSPy-Programming-not-prompting-LMs-skillsWrote 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/lebsral/dspy-programming-not-prompting-lms-skills/dspy-vllm)<a href="https://agentmods.dev/skills/lebsral/dspy-programming-not-prompting-lms-skills/dspy-vllm"><img src="https://agentmods.dev/badge/skills/lebsral/dspy-programming-not-prompting-lms-skills/dspy-vllm/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/lebsral/dspy-programming-not-prompting-lms-skills/dspy-vllm"><img src="https://agentmods.dev/badge/skills/lebsral/dspy-programming-not-prompting-lms-skills/dspy-vllm.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 | $0.00187 | $0.03146 |
| Opus 5 | $0.00093 | $0.01573 |
| Sonnet 5 | $0.00037 | $0.00629 |
| Haiku 4.5 | $0.00019 | $0.00315 |
Grade A, and why
dspy-vllm 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 9d 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.
curl http://localhost:8000/health The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 9d ago First seen · 279 lines · 187 tokens per session scan A 05b8d485ec86
dspy-vllm is a skill published in the GitHub repository lebsral/DSPy-Programming-not-prompting-LMs-skills (11 stars, last pushed 2mo ago), with no licence file. It adds 187 tokens to every session and 3,146 once invoked, about $0.0009 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 2026-09-03.
Other skills, from other repositories
ml-pipeline-workflow
Build end-to-end MLOps pipelines from data preparation through model training, validation, and production deployment. Use when creating ML pipelines, implementing MLOps practices, or automating model training and deployment workflows.
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…
lov-deploy-to-vercel
A deployment workflow for publishing Vite, Next.js, Create React App, or static frontend projects on Vercel, a hosting service for web applications. It can also connect a custom domain and configure Cloudflare DNS records.
bailian-train-deploy
A workflow for using Alibaba Cloud’s Bailian command-line tool to fine-tune or directly deploy AI models as callable services. It covers text, speech-synthesis, image-generation, and video-generation models.
arkcli-deploy
A deployment workflow for creating an online inference endpoint from an AI model. Creating one is a real account change that can create a billable resource.
ai-infrastructure-litellm
LiteLLM proxy server setup, TypeScript client patterns via OpenAI SDK, model routing, fallbacks, load balancing, spend tracking, virtual keys, and production deployment.