Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/shen-shanshan/vllm-dev-skills/vllm-rfc-generator)<a href="https://agentmods.dev/skills/shen-shanshan/vllm-dev-skills/vllm-rfc-generator"><img src="https://agentmods.dev/badge/skills/shen-shanshan/vllm-dev-skills/vllm-rfc-generator/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/shen-shanshan/vllm-dev-skills/vllm-rfc-generator"><img src="https://agentmods.dev/badge/skills/shen-shanshan/vllm-dev-skills/vllm-rfc-generator.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 | $0.00084 | $0.01149 |
| Opus 5 | $0.00042 | $0.00575 |
| Sonnet 5 | $0.00017 | $0.00230 |
| Haiku 4.5 | $0.00008 | $0.00115 |
Grade A, and why
vllm-rfc-generator 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 12d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vLLM RFC Generator
Generate a vLLM-style RFC Markdown document from user-provided information and save it to ./outputs/.
Inputs
Collect the following from the user (ask if not provided):
| Field | Required | Description |
|---|---|---|
| RFC Title | Yes | Short, descriptive title (will be prefixed with [RFC]:) |
| Main Content | Yes | Description of the motivation and proposed changes |
| Related PRs | No | List of PR numbers or URLs; classify them by category |
| Feedback Period | No | Duration for feedback (default: "At least 1 week") |
| CC List | No | GitHub usernames to CC (e.g., @user1, @user2) |
| Other Notes | No | Any additional context or notes |
Workflow
- Collect inputs — gather all necessary information from the user
- Classify PRs — if PRs are provided, group them by category (see PR Classification below)
- Generate RFC content — write each section following the template
- Save output — write to
./outputs/rfc-<slug>.md - Confirm — tell the user the output path
PR Classification
When the user provides related PRs, classify them into appropriate categories such as:
- Background / Motivation PRs — existing issues, bugs, or prior discussions that motivate this RFC
- Implementation PRs — concrete code changes implementing the proposed design
- Dependency PRs — prerequisite changes that must land first
- Related / Follow-up PRs — tangential improvements or future work inspired by this RFC
Format each category as a bullet list:
### Related PRs
**Background / Motivation:**
- [#XXXX](https://github.com/vllm-project/vllm/pull/XXXX): Brief description
**Implementation:**
- [#YYYY](https://github.com/vllm-project/vllm/pull/YYYY): Brief description
**Dependencies:**
- [#ZZZZ](https://github.com/vllm-project/vllm/pull/ZZZZ): Brief description
If a PR number has no description, fetch its title via the GitHub API or gh CLI:
gh pr view <NUMBER> --repo vllm-project/vllm --json title,url -q '"\(.url): \(.title)"'
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.
- 12d ago First seen · 131 lines · 84 tokens per session scan A 5a05651e89ba
vllm-rfc-generator is a skill published in the GitHub repository shen-shanshan/vllm-dev-skills (17 stars, last pushed 2d ago), licensed Apache-2.0. It adds 84 tokens to every session and 1,149 once invoked, about $0.0004 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
serving-llms-vllm
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
outlines
Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library.
ensembl-database
Query Ensembl genome database REST API for 250+ species. Gene lookups, sequence retrieval, variant analysis, comparative genomics, orthologs, VEP predictions, for genomic research.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
aatmf-t10-confidentiality-breach
AATMF T10 — Integrity & Confidentiality Breach. System prompt extraction, training-data extraction, model-weight leakage, private-key recovery.
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.