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 Abeautifulsnow/skills --skill review-workflowgit clone --depth 1 https://github.com/Abeautifulsnow/skillsWrote 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/abeautifulsnow/skills/review-workflow)<a href="https://agentmods.dev/skills/abeautifulsnow/skills/review-workflow"><img src="https://agentmods.dev/badge/skills/abeautifulsnow/skills/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/abeautifulsnow/skills/review-workflow"><img src="https://agentmods.dev/badge/skills/abeautifulsnow/skills/review-workflow.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00185 | $0.10701 |
| Opus 5 | $0.00093 | $0.05351 |
| Sonnet 5 | $0.00037 | $0.02140 |
| Haiku 4.5 | $0.00018 | $0.01070 |
Grade A, and why
review-workflow 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.
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.
How it starts
The opening of the file, as written. The whole thing — 788 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Workflow 编排 Skill
你是一个代码工作流编排助手，假设用户刚刚完成了一次代码变更。按以下步骤依次执行，并在步骤间传递完整上下文。
核心原则：没有背景信息的代码审查是不完整的。在看代码之前，必须先理解"为什么改"， 才能判断"改得对不对"，而不只是"改得规不规范"。
证据原则：不把猜测写成 finding，也不把证据不足的问题交给修复步骤。无法可靠判断时， 输出
needs deep review，说明缺少什么证据及最小验证，而不是为了完成流程硬给结论或补丁。
⚡ 执行模式
根据系统上下文中的 ultracode 状态自动选择：
- Ultracode 模式（已开启）：在可并行节点（Step 1.5+1.6、Step 4-B+4-C）使用
Agent工具并发执行，加速预审查和测试验证阶段 - 标准模式：按 Step 0 → 1 → 1.5 → 1.6 → ... → 6 顺序执行
可并行节点会在对应步骤标题下显式标注
【支持并发】。
子 Skill 路径注册表
本 Skill 在执行过程中会依次加载以下四个子 Skill。每个步骤开始前，必须先用 read 工具读取对应路径，以获取该 Skill 的完整执行规范，再按其规范执行。
| 子 Skill 名称 | 文件路径 | 在哪一步加载 |
|---|---|---|
review-preferences |
references/review-preferences | 第 0 步开始时 |
code-reviewer |
references/code-reviewer | 第 2 步开始前 |
parallel-debugging |
references/parallel-debugging | 第 3 步开始前 |
git-commit |
references/git-commit | 第 5 步开始前 |
⚠️ 重要：若对应路径的文件不存在，不得跳过或伪造该步骤的执行。 必须告知用户："子 Skill
<name>未找到（路径：<path>），请确认文件已创建。" 并等待用户处理后再继续。
第 0 步：获取变更背景（前置必填，读代码之前执行）
0-A 加载审查偏好
在做任何事之前，先用 read 工具读取：
📂 正在加载审查偏好：references/review-preferences
加载完成后，将其中的规则作为全局约束注入所有后续步骤。 若文件不存在，停止并告知用户，等待处理。
0-B 收集变更背景
在读取任何代码之前，必须先收集背景信息。 审查没有背景，结论不可靠。
向用户提问：
"在开始 review 之前，我需要了解这次变更的背景：
- 这次改动解决了什么问题，或实现了什么功能？（一句话也够，但必须回答）
- 是否有关联的提案/缺陷/需求？ 例如：
- JIRA 编号（如
PROJ-123）- GitHub Issue（如
#42）- TAPD 链接、设计文档等
有了背景，我才能判断代码改得"对不对"，而不只是"改得规不规范"。"
What ships with it
20 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.
- references/code-reviewer/references/code-quality-universal.md 9.4 KB
- references/code-reviewer/references/code-review-best-practices.md 3.7 KB
- references/code-reviewer/references/common-bugs-checklist.md 6.6 KB
- references/code-reviewer/references/go.md 13 KB
- references/code-reviewer/references/java.md 8.1 KB
- references/code-reviewer/references/nestjs.md 10 KB
- references/code-reviewer/references/python.md 11 KB
- references/code-reviewer/references/react.md 9.0 KB
- references/code-reviewer/references/rust.md 17 KB
- references/code-reviewer/references/security-review-guide.md 6.3 KB
- references/code-reviewer/references/svelte.md 11 KB
- references/code-reviewer/references/typescript.md 9.1 KB
- references/code-reviewer/references/vue.md 9.3 KB
- references/code-reviewer/SKILL.md 11 KB
- references/git-commit/SKILL.md 3.1 KB
- references/parallel-debugging/references/hypothesis-testing.md 3.3 KB
- references/parallel-debugging/SKILL.md 9.2 KB
- references/review-preferences/SKILL.md 1.3 KB
- scripts/diff_parse.py 15 KB runs code
- scripts/file_classify.py 7.3 KB runs code
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 · 788 lines · 185 tokens per session scan A 6d0f49402020
review-workflow is a skill published in the GitHub repository Abeautifulsnow/skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 185 tokens to every session and 10,701 once invoked, about $0.0009 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…