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 victorzhang016-code/hail-mary --skill hail-mary-cramgit clone --depth 1 https://github.com/victorzhang016-code/hail-maryWrote 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/victorzhang016-code/hail-mary/hail-mary-cram)<a href="https://agentmods.dev/skills/victorzhang016-code/hail-mary/hail-mary-cram"><img src="https://agentmods.dev/badge/skills/victorzhang016-code/hail-mary/hail-mary-cram/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/victorzhang016-code/hail-mary/hail-mary-cram"><img src="https://agentmods.dev/badge/skills/victorzhang016-code/hail-mary/hail-mary-cram.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 | $0.00221 | $0.05136 |
| Opus 5 | $0.00111 | $0.02568 |
| Sonnet 5 | $0.00044 | $0.01027 |
| Haiku 4.5 | $0.00022 | $0.00514 |
Grade A, and why
hail-mary-cram 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 11d 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 — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hail Mary Cram —— 临时抱佛脚备考框架
三件事：课件做索引 / 真题做主线 / 讲解奶奶都能听懂
何时启动 / 何时不启动
启动：
- 用户提到考试 / 复习 / 备考类关键词
- 已经 / 即将指定资料文件夹（课件 + 试卷）
- 时间紧，要"考场能默写"的版本，不要"教材级"长篇
不启动：
- 长期系统学习（这是"临时"抱佛脚）
- 学术论文 / 研究 / 写代码
- 用户只想要某个概念的 deep dive，没有考试场景
Phase 0：先建索引，再讲题（强制第一步）
进入 skill 后必须先做这件事，否则讲解会失焦、用户找不到出处。
Step 1 — 扫描资料文件夹，分流两类
- 课件 / 课程资料（关键词：
课件、slides、lecture、教材、reading、syllabus、concepts）→ 作为知识库索引（解释"为什么这么答"） - 试卷 / 真题（关键词：
试卷、真题、past paper、exam、midterm、final、assignment、exercise）→ 作为核心讲解对象
如果两类都找不到，停下来问用户在哪个文件夹。
Step 2 — 建立两份本地索引文件
在该文件夹建立（若已存在则更新而非覆盖）：
CLAUDE.md（考试基本信息 + 文件索引 + 选题策略）模板：
# {课程名} — 复习知识库
## 考试基本信息
- Section 结构：
- 时间：
- 题型与分值：
## 文件索引（有效资料）
| 文件 | 内容 | 优先级 |
|------|------|--------|
| xxx.pdf | xxx | ⭐⭐⭐ |
## 历年考点频率
| 考点 | 频率 | 优先级 |
|------|------|--------|
| xxx | x/x年 | 🔴 必考 |
## 考前选题策略（频率表跑完必填）
| 题号 | 主题 | 建议 | 难度 | 目标分 |
|---|---|---|---|---|
| Q1 | ... | ✅ 选 / ⚠️ 备选 / ❌ 跳 | ⭐⭐ | x-y/分值 |
**最佳 N 题组合**：__________
**预期总分**：__________
**跳哪块**：__________（原因）
## Section A/B 必背结构
（基于历年规律）
memory.md（对话过程中持续更新的笔记）模板：
# 备考过程笔记
## 已掌握
- (考点) — 已能默写，最后一次复习日期
## 仍混淆 / 易错
- (考点) — 卡在哪、对应的反例
## 易丢分细节
- ...
## 待预测命中（下次考试可能出）
- ...
Step 3 — 每轮讲解后回写
- 把新发现的高频考点写回
CLAUDE.md频率表 - 把用户卡住 / 反复问的点写回
memory.md的"仍混淆" - 让下次开新会话 Claude 一打开文件夹就有上下文
PDF 阅读策略（含扫描件 + 大文件）
| 情况 | 策略 |
|---|---|
| 原生 PDF ≤10 页 | 直接 Read 全读 |
| 原生 PDF >10 页 | 必须用 pages 参数分批，每次最多 20 页 |
| 扫描件 PDF（最常见） | 首选 pdftotext -layout 抽文本层 —— Git Bash / mingw 环境下 pdftotext 通常已装。试卷扫描件其实带 OCR 文本层的概率很高，别先放弃跳到多模态 Read。批量处理：for f in *.pdf; do pdftotext -layout "$f" "${f%.pdf}.txt"; done |
| 扫描件 PDF（pdftotext 抽出来是空 / 乱码） | 退回多模态 Read 试一次 → 仍失败问用户有没有同名 .txt（自己转过的）→ 都没有再考虑 OCR |
| 试卷里嵌入的图形（零件几何图、曲线图、流程图等） | pdftotext 抽不到图形，沙箱里 pdftoppm 经常被禁。第一时间主动提示用户截图发图，否则只能给方法论不能给精确答案。先用方法论开讲，等图到了再对照真实图重答 |
| 超大教材 (>50 页) | 先读目录页 + 章节首页定位重点，再按 pages 精准拉关键章节，禁止一次性全读 |
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.
- 11d ago First seen · 361 lines · 221 tokens per session scan A 8f39c9f17068
hail-mary-cram is a skill published in the GitHub repository victorzhang016-code/hail-mary (24 stars, last pushed 3mo ago), licensed MIT. It adds 221 tokens to every session and 5,136 once invoked, about $0.0011 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 2026-08-30.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.