agentmods.dev

vllm-rocm-pr-review

vllm-rocm-pr-review is a skill for Claude Code, Codex from shen-shanshan/vllm-dev-skills. It costs 0 tokens per session (4,870 once invoked), scanned A, original, Apache-2.0.

A review guide for pull requests involving AMD GPUs and ROCm, AMD's software platform for GPU computing, in the vLLM project. It produces a concise review report in Chinese.

In plain words
What is it for?
It is for reviewing vLLM pull requests related to AMD or ROCm changes and writing findings ordered by severity and grouped by type.
Why use it?
It gives reviewers a focused way to assess the purpose, code changes, risks, discussions, and final recommendation for these pull requests.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths.

not rated 25repo +4 changed yesterday A scan 0 tokens original Apache-2.0

Good fit It is for reviewing vLLM pull requests related to AMD or ROCm changes and writing findings ordered by severity and grouped by type.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/shen-shanshan/vllm-dev-skills/vllm-rocm-pr-review
View source ↗ shen-shanshan/vllm-dev-skills zhuanlan.zhihu.com
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 shen-shanshan/vllm-dev-skills --skill vllm-rocm-pr-review
Clone the repo
git clone --depth 1 https://github.com/shen-shanshan/vllm-dev-skills

Made for: Claude Code, Codex.

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-rocm-pr-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/shen-shanshan/vllm-dev-skills/vllm-rocm-pr-review/github.svg)](https://agentmods.dev/skills/shen-shanshan/vllm-dev-skills/vllm-rocm-pr-review)
Your own site
<a href="https://agentmods.dev/skills/shen-shanshan/vllm-dev-skills/vllm-rocm-pr-review"><img src="https://agentmods.dev/badge/skills/shen-shanshan/vllm-dev-skills/vllm-rocm-pr-review/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-rocm-pr-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/shen-shanshan/vllm-dev-skills/vllm-rocm-pr-review"><img src="https://agentmods.dev/badge/skills/shen-shanshan/vllm-dev-skills/vllm-rocm-pr-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,870 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.
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 $0.00000 $0.04870
Opus 5.5 $0.00000 $0.01948
Sonnet 5.5 $0.00000 $0.00974
Haiku 4.5 $0.00000 $0.00487

Measured yesterday against content hash 5da16e06bbc8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

vllm-rocm-pr-review 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 yesterday.

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.

skills/vllm-rocm-pr-review/SKILL.md · 281 lines

How it starts

The opening of the file, as written. The whole thing — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.

vLLM ROCm PR Review

Review a vllm-project/vllm PR through an AMD/ROCm lens, then write a single combined Chinese report to ./outputs/pr-<NUMBER>-review.md: Part A (§1–6) is a detailed PR summary in the style of the vllm-pr-summary skill, Part B (§7–8) is the ROCm review findings + verdict, and §9 holds 2–5 copy-paste English comments with file:line targets for the GitHub PR review UI. The vllm-pr-summary skill itself remains a separate, unchanged skill for standalone summary requests.

Knowledge sources (kept in references/):

File Content When to read
references/vllm-rocm-review-rules.md Curated rule catalog adapted from the ATOM/aiter review skills to vLLM's ROCm surface The mandatory checklist (Step 7)
references/upstream/atom-review-pr-skill.md Full upstream ATOM review-pr skill Deep reviews / new rule discovery
references/upstream/aiter-review-pr-skill.md Full upstream aiter review-pr skill Deep reviews / new rule discovery
references/upstream/mori-readme.md + mori-structure.json mori (AMD comm library) README + repo tree snapshot PRs touching mori / MORI-EP / moriio
references/example-report.md Style anchor for the combined report (Part A detailed summary + Part B findings) Before writing the report

Context economy: for quick reviews, read only the rule categories mapped by the PR type (Step 5) plus the core discipline section of the rules file. For deep reviews (Tier-1 backbone files touched, mori changes, perf claims), read the full rules file.

Workflow

  1. Fetch PR data — scripts/fetch_pr_data.py
  2. ROCm relevance gate
  3. Summary analysis → Part A content (detailed summary)
  4. Semantic understanding (5 questions)
  5. PR-type classification → mandatory rule categories
  6. Backbone-file risk assessment
  7. Apply the rule checklist
  8. AI-code diagnostic + blind-spot check
  9. Write the combined report (incl. §9 copy-paste English comments) to ./outputs/ and tell the user the path

Read the full file on GitHub · 281 lines

Files

What ships with it

60 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.

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. yesterday Changed 5da16e06bbc8
  2. 3d ago Changed · +27 lines 53c2358b4b41
  3. 1mo ago Changed · +71 lines · -137 tokens per session dd16a5da55f3
  4. 1mo ago First seen · 183 lines · 137 tokens per session scan A 0c49e46d8ea2

Subscribe to this mod's changes

vllm-rocm-pr-review is a skill published in the GitHub repository shen-shanshan/vllm-dev-skills (25 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 4,870 tokens. 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.

Claude CodeCode reviewHardware and IoTagent-skillssoftware-engineeringvLLMvibe-coding
Related

Other skills, from other repositories

gh-pr-review

Automated Cherry Studio review for local branches, PRs, commits, files, architecture docs, and repository skills. Use for code or documentation reviews that need project-specific naming, main/renderer/shared placement and dependency rules, IpcApi and DataApi boundaries, lifecycle/service ownership, renderer hooks…

CherryHQ/cherry-studio · 147 tokens

find-simplifications

Use when asked to find or plan Cherry Studio cleanup, simplification, refactoring, dead-code removal, duplicated state removal, unnecessary APIs, speculative generality, or library replacements, especially when the result should become evidence-backed proposed Agent Notes.

CherryHQ/cherry-studio · 53 tokens

github-review-pr

Review GitHub pull requests with detailed, multi-perspective code analysis using parallel subagents. Use this skill whenever the user wants to review a PR, asks for code review on a pull request, mentions "review PR", "check this PR", "look at pull request", or references a PR number or GitHub PR URL. Do NOT use for…

feiskyer/claude-code-settings · 90 tokens

plan-eng-review

Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations. Use when asked to "review the architecture", "engineering review", or "lock in the plan". Proactively suggest when…

GCWing/BitFun · 116 tokens

memstack-development-code-reviewer

Use this skill when the user says 'review code', 'code review', 'check my code', 'audit this', 'review PR', 'review changes', 'what's wrong with this', or is requesting a structured review of code quality, security, performance, or maintainability. Do NOT use for refactoring plans or test generation.

cwinvestments/memstack · 75 tokens

autoplan

Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. Surfaces taste decisions (close approaches, borderline scope, codex disagreements) at a final approval gate. One command, fully reviewed plan out. Use when…

GCWing/BitFun · 152 tokens