Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ggg123124/vrchat-assistantnpx agentmods add skills/ggg123124/vrchat-assistant/review-workflowWrote 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/ggg123124/vrchat-assistant/review-workflow)<a href="https://agentmods.dev/skills/ggg123124/vrchat-assistant/review-workflow"><img src="https://agentmods.dev/badge/skills/ggg123124/vrchat-assistant/review-workflow/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/ggg123124/vrchat-assistant/review-workflow"><img src="https://agentmods.dev/badge/skills/ggg123124/vrchat-assistant/review-workflow.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 | $0.00046 | $0.05215 |
| Opus 5 | $0.00023 | $0.02608 |
| Sonnet 5 | $0.00009 | $0.01043 |
| Haiku 4.5 | $0.00005 | $0.00522 |
Grade A, and why
review-workflow scanned grade A with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- 连通性分直连/代理两路实测;HTTP 200 空壳要**多客户端交叉验证**(curl 的 Schannel/无 HTTP/2 会被防护识别返回空壳,浏览器/node:https 正常)——单工具空壳不能下「源已死」结论。 Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **child_process 拼接命令**:可执行路径含空格被 cmd.exe 截断——`"${bin}"` 加引号;execFileSync 数组传参天然免疫。 How it starts
The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
审核工作流(PR / Issue / 协作审核)
本 skill 面向任何 AI Agent:当需要审核一个 PR 或 issue(判断可合并性/可关闭性、多轮修改复核、参与协作审核)时使用。沉淀自本仓库维护方多轮真实审核实践,通用方法可直接复用于其他 GitHub 仓库。
权威定义:仓库
DEVELOPMENT.md(PR 硬性要求 §2、跨平台约束 §3)、AGENT-REVIEW.md(协作审核协议)、AGENTS.md(Agent 义务)。本 skill 是执行方法论,冲突以仓库文档为准。
触发条件
- 使用者说「审核这个 PR / 看看能否合并 / 他又提交了 / 处理下这个 PR」
- 使用者说「看看这个 issue / 处理下 issue / 这个需求实现了吗 / 能不能关」
- 协作审核(AGENT-REVIEW 协议)中认领了 PR/issue,需要执行审核
- 维护方需要复核自己或他人 PR 的多轮修改
核心原则
- 审核只读,合并/关闭权归维护者:正式 review(APPROVE / REQUEST_CHANGES / COMMENT)与 issue 结论评论可提交,merge / push / close 必须先获得明确指令。「推荐合并」≠「授权合并」,选 review-only 就只提交意见。
- REST-only:gh CLI 的 GraphQL 命令(
gh pr list/gh pr view)对部分仓库会报Could not resolve to a Repository,但 REST(gh api repos/O/R/...)正常。一律用gh api(记得--paginate拿全量)。 - 端到端实测:不止读 diff——把 PR 文件提取到工作区实际运行(语法检查 / dry-run / mock 数据驱动)。很多问题只有跑起来才暴露(历史实例:
SqliteError: no such table、async IIFE 恒真值短路、删 return 的「语法合法但功能挂」)。 - 反馈分级:🔴 阻断项(合并前必修)/ ⚠️ 警告 / 💡 建议 / ✅ 通过项也要列出。
- 阻断项附实测证据:附报错输出/复现步骤,别只说理论——对方的 AI agent 会照做。自报「全部验证通过」≠ 可信,独立写验证脚本重跑。
- Agent 口吻:review/评论文字以 Agent 口吻陈述(可署背后使用者的账号,但不得用人类第一人称「我要…我做了…」)。
- 新贡献者身份独立判定:不默认贡献者是人或 agent。老账号+多个公开仓库+个人邮箱 commit = 人类特征;PR body null、工具化口吻 = agent 特征。身份存疑先
issues/N/comments询问,技术审查照常完成,最终处置等身份确认。 - 多轮 review 提交新评论,不编辑旧发言:R(n+1) 复核后提交新的 review(新 body + 新 inline),绝不 PATCH 编辑之前轮次的评论——review 链是历史记录。
审查流程
1. 收集上下文
gh api repos/O/R/pulls --jq '.[] | {number, title, user: .user.login, state, draft, created_at, updated_at}'
gh api repos/O/R/pulls/N --jq '{title, body, draft, state, head: .head.sha, head: .head.label, fork: .head.repo.fork, changed_files}'
gh api repos/O/R/pulls/N/files --paginate --jq '.[] | "\(.status) +\(.additions)/-\(.deletions) \(.filename)"'
gh api repos/O/R/pulls/N/commits --jq '.[] | "\(.sha[0:7]) \(.commit.message | split("\n")[0])"'
- ⚠️ 先对 remote 再动手:
git remote -v拿真实仓库名(cron prompt/记忆里的名字可能过时、写错导致 404 绕圈)。 - draft PR:GitHub 禁合并,评论照发但合并讨论等作者转 Ready for review。
- 「看 issue」≠「看 PR」:使用者说「扫描一下/提交了个新的」时同时查 open issues 和 open PRs。
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.
- 9d ago First seen · 198 lines · 46 tokens per session scan A 713a4bf1bd7c
review-workflow is a skill published in the GitHub repository ggg123124/vrchat-assistant (21 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 5,215 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
libretranslate-markdown-i18n
Machine-translate Markdown / Obsidian / Quartz content into other languages using a self-hosted LibreTranslate instance, preserving frontmatter, headings, emojis, bold/italic, wikilinks (![[...]]/[[...]]) and internal links. Use whenever a user wants to auto-translate a Markdown vault, Obsidian notes, or a…
awesome-skills-master
Master catalog orchestrator and autonomous installer for AI agents. Use when exploring, cloning, discovering, or installing skills, plugins, or MCP servers from awesome-skills without using interactive CLI tools. Guides environment detection, rule adaptation (.mdc/CLAUDE.md), MCP configuration, and strict author…
readme-template
Standard README template for repos — professional structure with badges, overview, table of contents, features/modules, stack, installation, configuration, tests, security, structure, docs, roadmap, contribute, license, author + RepoActivity sections (Star History, repo stats) + profile GIF footer. Use when creating…
suap-iff-api
Authenticate to and consume the SUAP IFF (Instituto Federal Fluminense) API v2 from the CLI — obtain the JWT access/refresh token via matricula+senha, then fetch student data (periodos letivos, dados do aluno, boletim). Use when the user has a suap.iff.edu.br matricula+senha and wants to extract academic data…
docker-single-port-multi-instance
Consolidate multiple Docker Compose app instances (production / test / demo) behind ONE host port using an nginx reverse proxy that routes by URL path prefix (e.g. /demo). Use when a user wants 'one port, several apps/banks' or a demo reachable simultaneously from the main landing page with its own database.
github-issue-pr-attribs
Standardize GitHub ISSUE and PR metadata (Assignee, Reviewer, Labels, Project, Milestone, Development, Relationship) and ship a strong, well-structured code-review template. Includes ready-to-use issue forms, PR template, and a severity/rubric review model.