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/aplaceforallmystuff/cheaters-generator/quickref-generatornpx skills add aplaceforallmystuff/cheaters-generator --skill quickref-generatorgit clone --depth 1 https://github.com/aplaceforallmystuff/cheaters-generatorWrote 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/aplaceforallmystuff/cheaters-generator/quickref-generator)<a href="https://agentmods.dev/skills/aplaceforallmystuff/cheaters-generator/quickref-generator"><img src="https://agentmods.dev/badge/skills/aplaceforallmystuff/cheaters-generator/quickref-generator.svg" alt="Measured on agentmods" 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 | $0.00029 | $0.01838 |
| Opus 5 | $0.00015 | $0.00919 |
| Sonnet 5 | $0.00006 | $0.00368 |
| Haiku 4.5 | $0.00003 | $0.00184 |
Grade B, and why
quickref-generator scanned grade B 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 3d 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
ls -la ~/.claude/skills/ How it starts
The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Quick-Reference Generator
Create a personalized Claude Code quick-reference system inspired by Brett Terpstra's Cheaters.
What This Skill Creates
A local HTML-based quick-reference system with:
- Modern design with oklch() colors and smooth animations
- Dark/light theme with system preference detection
- Per-sheet timestamps showing when each section was last updated
- "New" badges highlighting items added since previous generation
- Proper frontmatter parsing for skill descriptions and agent models
- Search functionality with keyboard navigation (j/k, /, Esc)
- LocalStorage persistence for last-viewed sheet and theme
Architecture
~/Dev/claude-code-quickref/ # Or your preferred location
├── index.html # Main HTML with navigation
├── stylesheets/
│ └── main.css # Modern oklch() theme styles
├── javascripts/
│ └── main.js # Auto-generated from sheets/
└── sheets/ # Individual sheet files (2-12 KB each)
├── builtin-commands.html
├── custom-skills.html
├── custom-agents.html
├── [plugin-name].html # One per installed plugin
├── mcp-[server-name].html # One per MCP server
└── ...
Frontmatter Parsing
Skills (SKILL.md)
The generator reads YAML frontmatter from each skill:
---
name: skill-name
description: What this skill does
user-invocable: true
---
Extracts:
description— Displayed in the quick-referenceuser-invocable— Whether users can invoke directly (shown with badge)
Agents (.md files)
The generator reads YAML frontmatter from each agent:
---
model: opus
tools:
- Read
- Write
---
Extracts:
model— Displayed as "Model: Opus/Sonnet/Haiku"tools— Listed in command-args section
Sheet File Format
Each sheet is a standalone HTML file with metadata:
<!-- meta: {"updatedAt": "2025-12-07T10:00:00", "hasNew": true} -->
<div class="sheet">
<h1>Sheet Title <span class="tag tag-custom">Custom</span></h1>
<p class="description">Brief description</p>
<h2>Section</h2>
<div class="command-grid">
<div class="command-card">
<div class="command-name">command_name</div>
<div class="command-desc">What it does (from frontmatter)</div>
<div class="command-args">Model: Opus | Tools: Read, Write</div>
</div>
</div>
</div>
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.
- 3d ago First seen · 254 lines · 29 tokens per session scan B 7f5114fb89d4
quickref-generator is a skill published in the GitHub repository aplaceforallmystuff/cheaters-generator (14 stars, last pushed 24d ago), licensed MIT. It adds 29 tokens to every session and 1,838 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
readable-py
Readable Python code rules inspired by The Art of Readable Code. Use when writing, reviewing, or refactoring Python code. Enforces short functions, flat control flow, clear naming, readable structure, and Pythonic idioms.
py
Comprehensive Python programming reference covering syntax, concurrency, networking, databases, ML/LLM development, and HPC. Use for: Python questions, Python interview preparation, debugging, performance optimization, async patterns, library examples, code review, best practices, MLOps workflows, distributed…
homepage-generator
Generate a fact-checked academic personal homepage from a CV, optionally augmented by an existing manual homepage and an assets directory. Produces editable structured source files (profile.yml + publications.bib + bio.md + news.md) and a single-file HTML page. Uses Codex MCP for independent factual review against…
render-html
Render an ARIS Markdown / JSON artifact (IDEAREPORT, AUTOREVIEW, KILLARGUMENT, PAPERPLAN, research-wiki state, etc.) into a single-file HTML view designed for human reading. Academic template outputs are gated by a fresh cross-model Codex review for render fidelity + safety (the ARIS invariant). Use when the user says…
readable-cpp
Readable C/C++/Rust/CUDA code rules inspired by The Art of Readable Code. Use when writing, reviewing, or refactoring C, C++, Rust, or CUDA code. Enforces short functions, flat control flow, clear naming, readable structure, and idiomatic patterns.
cpp
Comprehensive C/C++ programming reference covering everything from C11-C23 and C++11-C++23, system programming, CUDA GPU computing, debugging tools, Rust interop, and advanced topics. Use for: C/C++ questions, C/C++ interview preparation, modern language features, RAII/memory management, templates/generics, CUDA…