Borrowing it
Nothing to install: this file belongs to pensar-x/argus-validation-benchmarks. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/pensar-x/argus-validation-benchmarks/main/CLAUDE.mdgit clone --depth 1 https://github.com/pensar-x/argus-validation-benchmarksWrote 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/instructions/pensar-x/argus-validation-benchmarks/claude-md)<a href="https://agentmods.dev/instructions/pensar-x/argus-validation-benchmarks/claude-md"><img src="https://agentmods.dev/badge/instructions/pensar-x/argus-validation-benchmarks/claude-md.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 5.1 | $0.08584 | $0.08584 |
| Opus 5 | $0.04292 | $0.04292 |
| Sonnet 5 | $0.01717 | $0.01717 |
| Haiku 4.5 | $0.00858 | $0.00858 |
Grade A, and why
argus-validation-benchmarks CLAUDE.md 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 6d 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.
test: ["CMD", "curl", "-f", "http://localhost:3000/health"] How it starts
The opening of the file, as written. The whole thing — 1,020 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose: This document provides complete context for implementing the Apex benchmark suite. Read this entirely before beginning any work.
Table of Contents
- Project Overview
- What is Apex?
- Why Benchmarks?
- Benchmark Design Philosophy
- Technical Standards
- Directory Structure
- Implementation Checklist
- Benchmark Inventory
- Implementation Plans Reference
- Common Patterns
- Testing Requirements
- Quality Standards
Project Overview
What You're Building
You are implementing 60 vulnerable web applications (benchmarks) designed to evaluate the capabilities of Apex, an AI-powered autonomous penetration testing agent. Each benchmark is a self-contained, Dockerized application with a specific vulnerability that Apex must discover and exploit to capture a flag.
The Goal
Create a comprehensive evaluation suite that:
- Tests Apex's ability to find and exploit diverse vulnerability classes
- Covers modern tech stacks (Node.js, Python, Go, Java, PHP, Ruby)
- Includes difficulties from easy to hard
- Addresses gaps in existing benchmarks (like XBOW)
- Simulates real-world penetration testing scenarios
Success Criteria
Each benchmark must:
- Be fully self-contained (docker-compose up and it works)
- Have a retrievable flag via the intended vulnerability
- Include an automated solve script proving exploitability
- Follow the XBOW-compatible structure
- Be documented with attack walkthrough
What is Apex?
Apex is Pensar's AI-powered penetration testing agent. It autonomously:
- Discovers attack surfaces
- Identifies vulnerabilities
- Develops and executes exploits
- Chains multiple vulnerabilities
- Generates detailed security reports
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.
- 6d ago First seen · 1,020 lines · 8,584 tokens per session scan A 369da5db1cb4
argus-validation-benchmarks CLAUDE.md is an instructions file published in the GitHub repository pensar-x/argus-validation-benchmarks (59 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 8,584 tokens to every session, about $0.0429 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 2026-08-30.
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.
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.
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).
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).
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.
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.