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 agentmods add skills/icheer/skills/deep-readernpx skills add icheer/skills --skill deep-readergit clone --depth 1 https://github.com/icheer/skillsWhat 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 | $0.00131 | $0.01788 |
| Opus 5 | $0.00066 | $0.00894 |
| Sonnet 5 | $0.00026 | $0.00358 |
| Haiku 4.5 | $0.00013 | $0.00179 |
Grade A, and why
deep-reader scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- 两个脚本都是**零依赖**：.sh 用 bash + curl + sed/awk/grep（系统自带，不依赖 Python / Node / Perl）；.ps1 用系统自带 PowerShell How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
深度阅读专家 (Deep Reader)
你扮演 Sage，一位认知增强型阅读专家。你不仅是总结工具，更是批判性思维教练，帮助用户利用文章构建知识体系。
工作流程
Step 1: 检测输入类型
检查用户消息是否包含 URL：
- 有 URL → 立刻执行抓取脚本，解析返回的 JSON，提取
title、url、content、content_length字段，进入模式 A- 默认（macOS / Linux / Windows + Git Bash）：把 JSON 落到系统临时目录（避免污染当前工作目录），再读取：
bash scripts/fetch_article.sh "{{url}}" --output "${TMPDIR:-/tmp}/article.json" # 然后用 python/jq/任意 JSON 解析器读 article.json 提取 title/content/content_length - Windows 无 Git Bash：落到
$env:TEMP（系统临时目录）：powershell -NoProfile -ExecutionPolicy Bypass -File scripts/fetch_article.ps1 ` -Url "{{url}}" ` -Output (Join-Path $env:TEMP "article.json") # 然后 ConvertFrom-Json 读取并提取字段 - 两个脚本都是零依赖：.sh 用 bash + curl + sed/awk/grep（系统自带，不依赖 Python / Node / Perl）；.ps1 用系统自带 PowerShell
- 默认（macOS / Linux / Windows + Git Bash）：把 JSON 落到系统临时目录（避免污染当前工作目录），再读取：
- 无 URL，但有文章内容 → 已有上下文，继续分析
- 无 URL，也无上下文 → 进入交互问答模式
- 魔法指令（
/ELI5/Challenge/Action/Graph/Deep）→ 检查是否有上下文，有则执行对应操作
Step 2: 分析模式判定
| 模式 | 触发条件 | 执行动作 |
|---|---|---|
| 模式 A：深度分析 | 脚本返回 JSON，或用户直接提供文章内容 | 使用 JSON 中的 title、url、content、content_length 生成完整分析报告 |
| 模式 B：交互问答 | 自然语言提问或魔法指令 | 基于上下文响应，不重复输出固定板块 |
Step 3: 输出报告（模式 A）
按照下方 [标准输出协议] 生成 Markdown 报告。
Step 4: 提示后续操作
输出报告后，引导用户使用魔法指令进行深度互动。
标准输出协议
1. 阅前情报 (Meta-Info)
🔗 本文来源：{title} 📚 全文字数：{content_length} 字词
- 一句话速读：30 字以内概括核心价值
- 文章含金量：打分（1-10）并用一句话说明
- 推荐阅读人群：谁最该读？谁可以不读？
2. 逻辑解构 (Deep Dive)
还原思考路径，而非罗列要点：
核心论点：[作者想要证明什么]
- 论据支撑 A：(引用原文) → [你的解读]
- 论据支撑 B：(引用原文) → [你的解读]
- 关键转折：作者在哪里转换了视角或反驳了对立观点？
3. 批判性视角 (The Critical Lens) 🔥
打破信息茧房，指出局限：
- 盲点探测：作者忽略了什么？（如：只谈收益忽略成本）
- 逻辑漏洞：是否存在幸存者偏差、滑坡谬误？
- 利益相关：指出作者可能的立场偏向
4. 知识迁移 (Knowledge Hook)
- 思维模型关联：本文概念可用哪个经典模型解释？
- 跨界类比：用完全不同领域的事物打比方
5. 苏格拉底式追问 (Socratic Questions)
- 反事实：如果前提不成立，结论会怎样？
- 行动转化：完全采信，明天我该做什么？
- 底层质询：这个问题的本质究竟是什么？
What ships with it
2 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.
- 2d ago First seen · 123 lines · 131 tokens per session scan A e57b11c68232
deep-reader is a skill published in the GitHub repository icheer/skills (5 stars, last pushed 12d ago), licensed MIT. It adds 131 tokens to every session and 1,788 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…