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/layer1labs/specsmith/vllm-integrationnpx skills add layer1labs/specsmith --skill vllm-integrationgit clone --depth 1 https://github.com/layer1labs/specsmithWrote 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/layer1labs/specsmith/vllm-integration)<a href="https://agentmods.dev/skills/layer1labs/specsmith/vllm-integration"><img src="https://agentmods.dev/badge/skills/layer1labs/specsmith/vllm-integration.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 | $0.00022 | $0.00390 |
| Opus 5 | $0.00011 | $0.00195 |
| Sonnet 5 | $0.00004 | $0.00078 |
| Haiku 4.5 | $0.00002 | $0.00039 |
Grade A, and why
vllm-integration 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 Platform Integration
This skill enables specsmith projects to integrate with VLLM for large language model serving while maintaining governance compliance.
Requirements Covered
- REQ-110: VLLM Platform Integration
- Allows specsmith projects to integrate with VLLM for large language model serving with human approval
Integration Capabilities
Platform Features
- VLLM model serving and deployment
- GPU and CPU resource management
- Model optimization and quantization
- API endpoint configuration for VLLM services
- Performance monitoring and tuning
Governance Requirements
- Human approval required for all VLLM integrations
- Configuration management with governance controls
- Security best practices enforcement
- Resource monitoring and logging
Usage Examples
# Initialize VLLM integration
specsmith skill install vllm-integration
# Configure VLLM platform settings
specsmith vllm configure --platform vllm --model-path /path/to/model --gpu-count 2
# Deploy model via VLLM
specsmith vllm deploy --model my-model --port 8000
Configuration
The skill requires the following configuration in scaffold.yml:
vllm:
platform: vllm
model_path: /path/to/models
gpu_count: 2
port: 8000
quantization: "none"
Security Considerations
- All VLLM integrations require human approval
- Model access controls must be configured
- Network security must be enforced
- Resource usage monitoring is required
Compliance Requirements
- Follow security best practices for AI platform integrations
- Maintain audit logs of all VLLM interactions
- Ensure proper resource management and monitoring
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 · 68 lines · 22 tokens per session scan A f55cccdfdac9
vllm-integration is a skill published in the GitHub repository layer1labs/specsmith (7 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 390 once invoked, about $0.0001 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
embed
Generate, inspect, and use node/text embeddings in Semantica — compute Node2Vec embeddings, find similar nodes, score link predictions, batch similarity, and pairwise similarity. Uses NodeEmbedder, SimilarityCalculator, LinkPredictor, and AgentContext. Sub-commands: compute, similar, similarity, predict-link…
reason
Run reasoning over the Semantica knowledge graph — deductive logic, abductive hypothesis generation, Datalog programs, SPARQL queries, Rete network evaluation. Uses DeductiveReasoner, AbductiveReasoner, DatalogReasoner, SPARQLReasoner, ReteEngine. Sub-commands: deductive, abductive, datalog, sparql, rete, prove…
validate
Validate Semantica pipelines, extraction quality, graph schemas, and ontology consistency. Returns structured error/warning checklists. Uses PipelineValidator, PipelineBuilder.validatepipeline(), GraphValidator, and OntologyValidator. Sub-commands: pipeline, step, dependencies, extraction, graph, ontology, performance.
extract
Run the full Semantica semantic extraction pipeline on a file or selected text — NER, relations, events, coreference resolution, triplets, and validation. Clears result cache before each run. Returns Markdown tables with entity/relation/event/triplet results and inline validator warnings.
change
Track and inspect graph changes, diffs, temporal updates, and the impact of new data on Semantica knowledge graphs.
ingest
Ingest data from files, databases, APIs, or streams into Semantica knowledge graphs with schema mapping and entity linking.