skills CLAUDE.md

skills CLAUDE.md is an instructions file for coding agents from Quant-Off/skills. It costs 1,385 tokens per session, scanned A, original, MIT.

A set of instructions for working on the Quant-Off security-research plugin marketplace and its files.

In plain words
What is it for?
Use it when creating or editing marketplace manifests, plugins, skills, commands, agents, or hooks in that repository.
Why use it?
It helps an agent follow the repository’s required file layout and contribution rules when changing plugins or skills.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/quant-off/skills/claude-md
Clone the repo
git clone --depth 1 https://github.com/Quant-Off/skills

Wrote 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.

agentmods badge for skills CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/quant-off/skills/claude-md.svg)](https://agentmods.dev/instructions/quant-off/skills/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/quant-off/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/quant-off/skills/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,385 This file is loaded in full into every session.
When invoked 1,385 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.01385 $0.01385
Opus 5 $0.00692 $0.00692
Sonnet 5 $0.00277 $0.00277
Haiku 4.5 $0.00138 $0.00138

Measured 3d ago against content hash e5c8fcce70ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skills CLAUDE.md 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 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.

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.

CLAUDE.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Directives for Claude Code when working in this repository. Follow these rules whenever you create or modify files here. The human contribution workflow lives in CONTRIBUTING.md; this file is the operating manual for the agent.

Repository context

Quant-Off/skills is a Claude Code plugin marketplace for security research. Each plugin bundles one or more skills that let Claude Code verify cryptographic code, analyze binary artifacts with Ghidra, and audit codebases accurately and repeatably.

Structural rules (never violate)

  • .claude-plugin/marketplace.json lives at the repo root, never inside a plugin.
  • A plugin's plugin.json lives at plugins/<name>/.claude-plugin/plugin.json.
  • Skills, commands, agents, and hooks live at the plugin root (plugins/<name>/skills/...), never inside .claude-plugin/.
  • Skills auto-discover from the plugin's skills/ directory; no extra declaration is needed unless a custom path is used.

Repository layout:

.
├── .claude-plugin/
│   └── marketplace.json          # Marketplace manifest (MUST stay at repo root)
├── plugins/                      # One directory per plugin
│   └── <plugin-name>/
│       ├── .claude-plugin/
│       │   └── plugin.json        # Plugin manifest
│       ├── skills/
│       │   └── <skill-name>/
│       │       ├── SKILL.md        # Entry point, under 500 lines
│       │       ├── references/     # Detail loaded on demand, one level deep
│       │       └── scripts/        # Optional executable helpers
│       └── README.md
├── CLAUDE.md                     # This file (Claude Code directives)
├── CONTRIBUTING.md               # Contribution guide (English)
├── CONTRIBUTING_KR.md            # Contribution guide (Korean)
├── README.md                     # English docs
├── README_KR.md                  # Korean translation
└── LICENSE

Marketplace facts

  • The marketplace name is quant-security (from marketplace.json).
  • Each plugin's source is a repo-relative path (./plugins/<name>), so everything ships from this single repository.
  • Install path for users: /plugin marketplace add Quant-Off/skills then /plugin install <plugin-name>@quant-security.

Read the full file on GitHub · 125 lines

Changes

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.

  1. 3d ago First seen · 125 lines · 1,385 tokens per session scan A e5c8fcce70ec

Subscribe to this mod's changes

skills CLAUDE.md is an instructions file published in the GitHub repository Quant-Off/skills (1 stars, last pushed 24d ago), licensed MIT. It adds 1,385 tokens to every session, about $0.0069 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.