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/amd-aim/inference-skill/vllm-optimizenpx skills add AMD-AIM/inference-skill --skill vllm-optimizegit clone --depth 1 https://github.com/AMD-AIM/inference-skillWrote 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/amd-aim/inference-skill/vllm-optimize)<a href="https://agentmods.dev/skills/amd-aim/inference-skill/vllm-optimize"><img src="https://agentmods.dev/badge/skills/amd-aim/inference-skill/vllm-optimize.svg" alt="Measured on agentmods" 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 | $0.00049 | $0.00530 |
| Opus 5 | $0.00024 | $0.00265 |
| Sonnet 5 | $0.00010 | $0.00106 |
| Haiku 4.5 | $0.00005 | $0.00053 |
Grade A, and why
vllm-optimize 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
vLLM Optimize
Automated vLLM inference benchmark and profiling workflow for containerized environments.
Quick Start
Run the workflow with a model name:
use vllm-optimize skill for Qwen/Qwen3.5-35B-A3B
The skill will automatically:
- Start vLLM server with the specified model
- Run benchmark at various concurrency levels
- Generate profiling traces
- Analyze GPU kernel performance
First-turn Latency Rule
- Do not read any other file before the first visible reply
- Send one short kickoff status update explaining the workflow
- Ask the first grouped setup form with options
Guided Setup Flow
-
Start with one short high-level question round:
Run plan(smoke test vs full sweep)Output(where to save results)GPUs(which GPUs to use)
-
After Round 1 answers, read
INTAKE.mdfor deeper config -
Read
RUNTIME.mdfor execution bootstrap -
Summarize the final plan and get confirmation before executing
-
After confirmation, start execution following phase docs
Modes
full: benchmark + profiling + analysisbenchmark: benchmark only (faster)profile: profiling only (requires server running)
Files to Read
- Before Round 1: no extra file reads required
- After Round 1 answers:
INTAKE.md - Before execution:
RUNTIME.md - Phase docs:
phases/*.md
References
INTAKE.md- Configuration optionsRUNTIME.md- Execution details- Phase 1: vLLM Server Setup
- Phase 2: Benchmark Execution
- Phase 3: Profiling
- Phase 4: Analysis
What ships with it
8 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 · 70 lines · 49 tokens per session scan A c3d28b29ede6
vllm-optimize is a skill published in the GitHub repository AMD-AIM/inference-skill (5 stars, last pushed 3mo ago), licensed MIT. It adds 49 tokens to every session and 530 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 2026-08-31.
Other skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
mixed-precision
Use FP16/BF16 mixed precision to accelerate training and reduce memory. Use when optimizing GPU performance.
oracle
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
summarize-document
Summarize a long PDF, scan, office file, text file, or markdown file through the connected Superlinked MCP edge instead of reading the whole source into model context. Use when the user asks for a summary, overview, digest, or "what does this document say" about a large file.
generate-codebook
Generate a citable data dictionary / codebook from a tabular dataset (CSV/TSV/Excel/Parquet/Stata/SAS). Profiles every variable — role, type, units placeholder, level frequencies, range/quantiles, missingness — and emits codebook.md + codebook.json. Flags coded variables whose level meanings are unknown as [NEEDS…
nvalchemi-model-wrapping
How to wrap an arbitrary MLIP (Machine Learning Interatomic Potential) using the BaseModelMixin interface to standardize inputs, outputs, and embeddings. Use when integrating a model such as MACE or AIMNet2 (e.g. MACEWrapper, loading pretrained checkpoints) so dynamics, training, or fine-tuning stages can call it, or…