vllm-backport-fetch-prs

vllm-backport-fetch-prs is a skill for Claude Code from opendatahub-io/ai-helpers. It costs 62 tokens per session (420 once invoked), scanned A, original, Apache-2.0.

A tool that fetches recently merged bug-fix pull requests from the vLLM GitHub project within a chosen date range. vLLM is an open-source software project for serving large language models.

In plain words
What is it for?
Use it at the start of a backport review to collect pull-request details, labels, authors, merge commits, and possible reverts.
Why use it?
It provides the raw list needed to begin checking which upstream fixes may need to be transferred to another release or branch.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the odh-vllm plugin — 8 skills shipped together

Good fit Use it at the start of a backport review to collect pull-request details, labels, authors, merge commits, and possible reverts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/opendatahub-io/ai-helpers/vllm-backport-fetch-prs
Install

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.

Any agent
npx skills add opendatahub-io/ai-helpers --skill vllm-backport-fetch-prs
Clone the repo
git clone --depth 1 https://github.com/opendatahub-io/ai-helpers

Made for: Claude Code.

Or install odh-vllm, the plugin that ships this one along with the rest of its 8 skills.

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.

agentmods badge for vllm-backport-fetch-prs

README.md
[![agentmods](https://agentmods.dev/badge/skills/opendatahub-io/ai-helpers/vllm-backport-fetch-prs/github.svg)](https://agentmods.dev/skills/opendatahub-io/ai-helpers/vllm-backport-fetch-prs)
Your own site
<a href="https://agentmods.dev/skills/opendatahub-io/ai-helpers/vllm-backport-fetch-prs"><img src="https://agentmods.dev/badge/skills/opendatahub-io/ai-helpers/vllm-backport-fetch-prs/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.

agentmods 80×15 button for vllm-backport-fetch-prs

Your own site · 80×15
<a href="https://agentmods.dev/skills/opendatahub-io/ai-helpers/vllm-backport-fetch-prs"><img src="https://agentmods.dev/badge/skills/opendatahub-io/ai-helpers/vllm-backport-fetch-prs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 420 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00062 $0.00420
Opus 5 $0.00031 $0.00210
Sonnet 5 $0.00012 $0.00084
Haiku 4.5 $0.00006 $0.00042

Measured 9d ago against content hash 9e7e3b32d58f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

vllm-backport-fetch-prs 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 9d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/fetch-bugfix-prs.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/odh-vllm/skills/vllm-backport-fetch-prs/SKILL.md · 53 lines

What it actually says

Fetch Bugfix PRs

Fetches merged bugfix PRs from vllm-project/vllm using multiple GitHub search queries (label:bug, [Bugfix]/[BugFix]/[Bug Fix] in title) and deduplicates results. Also detects reverted PRs.

Usage

bash scripts/fetch-bugfix-prs.sh [DAYS_BACK]
  • DAYS_BACK — number of days to look back (default: 7)
  • stdout — JSON array of PR objects
  • stderr — progress messages

Output Schema

Each PR object contains:

  • number, title, mergedAt, mergeCommit.oid
  • labels, author.login, mergedBy.login
  • label_names — flattened list of label strings
  • reverted_by — PR number that reverted this one (or null)

Example

mkdir -p artifacts/backport-triage
bash scripts/fetch-bugfix-prs.sh 14 > artifacts/backport-triage/raw-prs.json

Determining DAYS_BACK

Check the latest report directory to auto-detect how far back to look:

LAST=$(ls -1d reports/<version>/*/ 2>/dev/null | tail -1)

If no previous report exists, compute days since the release date.

Files

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.

Changes

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.

  1. 9d ago First seen · 53 lines · 62 tokens per session scan A 9e7e3b32d58f

Subscribe to this mod's changes

vllm-backport-fetch-prs is a skill published in the GitHub repository opendatahub-io/ai-helpers (37 stars, last pushed 5d ago), licensed Apache-2.0. It adds 62 tokens to every session and 420 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.

Related

Other skills, from other repositories

git-advanced-workflows

Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.

wshobson/agents · 54 tokens

workflow-patterns

Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.

wshobson/agents · 35 tokens

block-no-verify-hook

Configure a PreToolUse hook to prevent AI agents from skipping git pre-commit hooks with --no-verify and other bypass flags. Use when setting up Claude Code projects that enforce commit quality gates.

wshobson/agents · 46 tokens

turborepo-caching

Configure Turborepo for efficient monorepo builds with local and remote caching. Use when setting up Turborepo, optimizing build pipelines, or implementing distributed caching.

wshobson/agents · 42 tokens

ainb-fleet:ainb-spawn

Spawn a coding-agent session correctly with ainb run: always into a git worktree, never bare into a plain checkout. Use whenever you are about to start a Claude/Codex/Gemini/Copilot session in a terminal. Guards the invocations that silently produce a (broken) workspace row, two agents sharing one working tree, a…

stevengonsalvez/agents-in-a-box · 107 tokens

Finishing a Development Branch

Clean branch finalization, squashing commits, and updating changelogs before merging.

ankur-gaurav161418/omniforge · 23 tokens