red-team-agent-skills: Instructions file for Claude Code

CLAUDE.md

red-team-agent-skills CLAUDE.md is an instructions file for Claude Code from yechao-zhang/red-team-agent-skills. It costs 795 tokens per session, scanned A, original, MIT.

A repository of security-testing skills for Claude Code, including red-team testing and an agent-proxy skill for examining agent behavior and tool use.

In plain words
What is it for?
Use it when setting up the repository's red-team or agent-proxy skills, running their browser-based workflows, or optionally capturing lessons into project instructions.
Why use it?
It documents how to install these skills locally or globally and lists the dependencies and optional self-learning setup they need.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is yechao-zhang/red-team-agent-skills's own configuration. It tells Claude Code how to work on red-team-agent-skills itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything red-team-agent-skills configures →

Reuse

Borrowing it

Nothing to install: this file belongs to yechao-zhang/red-team-agent-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/yechao-zhang/red-team-agent-skills/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/yechao-zhang/red-team-agent-skills

Made for: Claude Code.

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 red-team-agent-skills CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/yechao-zhang/red-team-agent-skills/claude-md/github.svg)](https://agentmods.dev/instructions/yechao-zhang/red-team-agent-skills/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/yechao-zhang/red-team-agent-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/yechao-zhang/red-team-agent-skills/claude-md/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.

agentmods 80×15 button for red-team-agent-skills CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/yechao-zhang/red-team-agent-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/yechao-zhang/red-team-agent-skills/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 795 This file is loaded in full into every session.
When invoked 795 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00795 $0.00795
Opus 5 $0.00398 $0.00398
Sonnet 5 $0.00159 $0.00159
Haiku 4.5 $0.00080 $0.00080

Measured 11d ago against content hash 826e1645b81d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

red-team-agent-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 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.

CLAUDE.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Installation & Setup

1. Skill Installation

Option A: Project-Local Use (Recommended for Development)

You can use the skills directly from this repository without global installation.

  1. Open this directory in Claude Code: claude (from the root of this repo).
  2. The skills in .claude/skills/ (red-team, agent-proxy) will be automatically loaded.

Option B: Global Installation

To use these skills globally across any project:

  1. Create the global skills directory: mkdir -p ~/.claude/skills
  2. Copy the skills:
    cp -r .claude/skills/red-team ~/.claude/skills/
    cp -r .claude/skills/agent-proxy ~/.claude/skills/
    

Optional: Claude Reflect (Self-Learning)

You can install claude-reflect to capture learnings and update CLAUDE.md automatically.

# Clone and install claude-reflect
git clone https://github.com/BayramAnnakov/claude-reflect ~/.claude/skills/claude-reflect
# Note: No pip requirements for this skill (uses standard library)

2. Dependencies

Install Python dependencies (required for red-team and agent-proxy):

pip install -r .claude/skills/red-team/requirements.txt
pip install -r .claude/skills/agent-proxy/requirements.txt

3. Browser Automation Setup (Required for Web UIs)

For testing Web UI agents (like ChatGPT, Claude, custom UIs), you must install one of the browser automation skills.

Option A: dev-browser (Recommended)

This skill provides persistent sessions (cookies/storage), better stealth, and profile management.

Install via MCP (recommended): Check if dev-browser is available in your MCP configuration.

Install manually: If you have access to the dev-browser repository:

# Clone and install dev-browser skill
git clone https://github.com/SawyerHood/dev-browser.git ~/.claude/skills/dev-browser
cd ~/.claude/skills/dev-browser
# Follow installation instructions in its README (usually npm install & build)

Option B: playwright-skill (Alternative)

Standard Playwright automation. Use this if dev-browser is not available.

Read the full file on GitHub · 87 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. 11d ago First seen · 87 lines · 795 tokens per session scan A 826e1645b81d

Subscribe to this mod's changes

red-team-agent-skills CLAUDE.md is an instructions file published in the GitHub repository yechao-zhang/red-team-agent-skills (5 stars, last pushed 7mo ago), licensed MIT. It adds 795 tokens to every session, about $0.0040 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens