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 amazing-fish/agent-skills --skill explain-diff-for-human-reviewgit clone --depth 1 https://github.com/amazing-fish/agent-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/amazing-fish/agent-skills/explain-diff-for-human-review)<a href="https://agentmods.dev/skills/amazing-fish/agent-skills/explain-diff-for-human-review"><img src="https://agentmods.dev/badge/skills/amazing-fish/agent-skills/explain-diff-for-human-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.
<a href="https://agentmods.dev/skills/amazing-fish/agent-skills/explain-diff-for-human-review"><img src="https://agentmods.dev/badge/skills/amazing-fish/agent-skills/explain-diff-for-human-review.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 | $0.00107 | $0.03489 |
| Opus 5 | $0.00053 | $0.01744 |
| Sonnet 5 | $0.00021 | $0.00698 |
| Haiku 4.5 | $0.00011 | $0.00349 |
Grade A, and why
explain-diff-for-human-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 10d 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
生成人工代码检视报告
修改说明：本文件从
GitHubxsy/agent-skills引入，并由amazing-fish/agent-skills修改了报告输出位置、规模控制、GitHub 固定链接证据策略、可选独立子 Agent 审查和明暗主题视觉基线。来源与上游版本见仓库根目录sources.lock.json。
生成一份自包含的 HTML 报告，将原始代码差异转化为供人类检视的上下文、证据和待确认事项。帮助检视者作出判断，不要替检视者自动批准改动，也不要只复述增加或删除了哪些代码行。
确定检视范围
- 准确解析用户指定的目标：单个提交、提交范围、分支比较、代码评审请求（PR 或 MR）、暂存区、工作区或指定文件。
- 如果目标不明确，使用对话中最近讨论的一组改动，并在报告中明确说明该假设。
- 检查 diff、改动前的代码、相关调用方、测试、配置和文档。
- 区分代码中可以确认的事实和对修改意图的推断；对不确定的结论加以标注。
- 除非用户另行要求修复，否则在解释 diff 时不要修改产品代码。
优先使用仓库原生命令，例如：
git show --stat --oneline <commit>
git diff <base>...<head>
git show <commit> -- <path>
rg "<symbol>" <relevant-paths>
生成报告
不要将运行生成物默认写入 Skill 安装目录。按以下优先级确定一个 UTF-8 HTML5 输出文件：
- 用户显式指定的文件或目录。
- 当前仓库根目录下的
reports/explain-diff-<target>.html。 - 当前可写工作区下的
reports/explain-diff-<target>.html。 - 无仓库和工作区时，系统临时目录下的
reports/explain-diff-<target>.html。
如果本 Skill 包含 scripts/resolve_report_path.py，优先用它确定路径并创建父目录。显式路径以 .html 结尾时视为文件，否则视为目录。始终在最终响应中返回实际绝对路径。Skill 安装目录只有在用户明确指定时才可作为输出位置。
报告必须能够通过直接打开文件使用：
- 将全部 CSS 内嵌到 HTML。
- 不使用远程字体、脚本、样式表、图片、分析服务或其他托管资源。
- 使用语义化 HTML、响应式布局、清晰的键盘焦点和足够的文字对比度。
- 将代码、路径、提交信息以及用户提供的文本写入 HTML 前进行转义。
- 优先使用 CSS 图示和带标签的流程图；仅在确实有助于理解关系时使用内联 SVG。
- 使用
<details>折叠较长的代码片段、验证命令和问答答案。 - 如果代码托管平台提供稳定的网页地址，链接到具体提交、文件和代码行；支持 GitHub、CodeHub、GitLab、Gitee 及其他类似平台，不绑定任何特定厂商。
- 优先使用固定到提交哈希的永久链接，不使用可能随分支变化而失效的链接。
- 先读取仓库 remote，并仅在能够可靠识别托管平台及其 URL 规则时生成网页链接。不要根据猜测拼接地址。
- 如果托管平台未知、没有网页访问地址或无法确定链接格式，则显示仓库相对路径、符号、提交哈希和行号，不降低报告的可读性。
- 提供打印样式，确保报告导出为 PDF 后仍然可读。
如果本 Skill 包含 assets/report-theme.css，将它作为报告视觉基线，并把完整内容内联到 HTML 的 <style>；不要从生成报告链接该文件。扩展样式时继续使用其中的语义 --color-* token，不要在组件规则中散落新的颜色值。保留以下主题契约：
- 以
:root定义浅色 token，以prefers-color-scheme: dark仅覆盖同一组 token；不使用 JavaScript 切换主题。 - 页面、内容表面、导航、链接、代码、表格、发现、验证状态、边框和焦点指示均使用语义 token；状态还必须有文字或形状标记，不能只靠颜色传意。
- 普通文字、链接和状态文字与其背景至少达到 4.5:1；键盘焦点指示与相邻表面至少达到 3:1。
- 保留响应式规则，以及强制浅色、高对比、无阴影和非粘性导航的打印 token/布局；屏幕处于深色模式时打印仍应节墨且清晰。
控制报告规模
生成 HTML 前统计 changed files、增加/删除行数、可获得的 patch 字节数，以及缺失 patch 的文件数。如果本 Skill 包含 scripts/classify_diff_size.py，使用它选择模式；默认阈值为：
What ships with it
5 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.
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.
- 10d ago First seen · 190 lines · 107 tokens per session scan A bcba45cb6111
explain-diff-for-human-review is a skill published in the GitHub repository amazing-fish/agent-skills (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 107 tokens to every session and 3,489 once invoked, about $0.0005 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.