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 opendatahub-io/ai-helpers --skill vllm-backport-classifygit clone --depth 1 https://github.com/opendatahub-io/ai-helpersWrote 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/opendatahub-io/ai-helpers/vllm-backport-classify)<a href="https://agentmods.dev/skills/opendatahub-io/ai-helpers/vllm-backport-classify"><img src="https://agentmods.dev/badge/skills/opendatahub-io/ai-helpers/vllm-backport-classify/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/opendatahub-io/ai-helpers/vllm-backport-classify"><img src="https://agentmods.dev/badge/skills/opendatahub-io/ai-helpers/vllm-backport-classify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00063 | $0.00435 |
| Opus 5 | $0.00032 | $0.00217 |
| Sonnet 5 | $0.00013 | $0.00087 |
| Haiku 4.5 | $0.00006 | $0.00044 |
Grade A, and why
vllm-backport-classify 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 8d 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
Classify and Filter
Applies deterministic regex rules to classify PRs, checks which files existed at the target release tag, detects subsystems, and filters out PRs that only touch post-release or non-runtime code.
Usage
python3 scripts/classify-and-filter.py \
--input artifacts/backport-triage/raw-prs.json \
--repo /path/to/vllm \
--tag v0.13.0 \
--output artifacts/backport-triage/filtered.json
Input
raw-prs.json — output of the vllm-backport-fetch-prs skill.
Output
filtered.json — same PR objects enriched with:
classification:runtime_bug,platform_specific,unclear,not_bugfixverdict:CANDIDATEorSKIPskip_reason: why skipped (if applicable)files,files_in_release,files_new,files_in_release_count,files_totalsubsystems: list of detected vLLM subsystem names
Agent Follow-up
After running this skill, review PRs with classification: "unclear". Read
each PR's description and decide if it's a real bugfix. Override the
classification in the JSON if needed.
Bugfix PRs in vLLM often have misleading titles — always check the actual diff and description, not just the title.
What ships with it
1 file 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.
- 8d ago First seen · 52 lines · 63 tokens per session scan A fcdd30e9f619
vllm-backport-classify is a skill published in the GitHub repository opendatahub-io/ai-helpers (37 stars, last pushed 4d ago), licensed Apache-2.0. It adds 63 tokens to every session and 435 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…
saga-orchestration
Implement saga patterns for distributed transactions and cross-aggregate workflows. Use this skill when implementing distributed transactions across microservices where 2PC is unavailable, designing compensating actions for failed order workflows that span inventory, payment, and shipping services, building…
task-coordination-strategies
Decompose complex tasks, design dependency graphs, and coordinate multi-agent work with proper task descriptions and workload balancing. Use this skill when breaking down work for agent teams, managing task dependencies, or monitoring team progress.
bazel-build-optimization
Optimize Bazel builds for large-scale monorepos. Use when configuring Bazel, implementing remote execution, or optimizing build performance for enterprise codebases.
nx-workspace-patterns
Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.
context-driven-development
Creates and maintains project context artifacts (product.md, tech-stack.md, workflow.md, tracks.md) in a conductor/ directory. Scaffolds new projects from scratch, extracts context from existing codebases, validates artifact consistency before implementation, and synchronizes documents as the project evolves. Use when…