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 instructions/yee-yore/dorkagent/claude-mdgit clone --depth 1 https://github.com/yee-yore/DorkAgentWrote 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/yee-yore/dorkagent/claude-md)<a href="https://agentmods.dev/instructions/yee-yore/dorkagent/claude-md"><img src="https://agentmods.dev/badge/instructions/yee-yore/dorkagent/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 | $0.01888 | $0.01888 |
| Opus 5 | $0.00944 | $0.00944 |
| Sonnet 5 | $0.00378 | $0.00378 |
| Haiku 4.5 | $0.00189 | $0.00189 |
Grade A, and why
DorkAgent 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 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.
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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
DorkAgent is a LLM-powered automated Google Dorking tool for security research, bug bounty hunting, and penetration testing reconnaissance. It uses the CrewAI framework to coordinate AI agents that discover potential security vulnerabilities and exposed sensitive information in target domains through passive reconnaissance only.
Commands
Running the Tool
# Interactive mode (menu-driven interface)
python dorkagent.py
# Note: CLI mode (dorkagent-cli.py) is not yet implemented
Package Installation
The application automatically installs missing dependencies on first run. Manual installation:
# Python 3.11.9 recommended
pip install python-dotenv crewai crewai-tools "crewai[anthropic]" "crewai[google-genai]" "crewai-tools[serpapi]" termcolor prompt-toolkit pyfiglet schedule
Environment Setup
Create .env file with required API keys:
SERPER_API_KEY= # Required if using Serper as the search engine - https://serper.dev/
SERPAPI_API_KEY= # Required if using SerpApi as the search engine - https://serpapi.com/manage-api-key
OPENAI_API_KEY= # Optional - set if using OpenAI
ANTHROPIC_API_KEY= # Optional - set if using Anthropic
GEMINI_API_KEY= # Optional - set if using Gemini (recommended for free usage)
High-Level Architecture
Modular Structure
The codebase follows a modular architecture after the v1.4 refactoring:
- dorkagent.py: Main entry point with orchestration logic, handles dependency installation, banner display, and CrewAI workflow execution
- config.py: LLM configuration and API key management (selection, validation, instantiation)
- agents.py: CrewAI agent definitions (searcher, bughunter, writer)
- tasks.py: CrewAI task definitions with Google Dork queries and analysis prompts
- utils.py: Utility functions for domain input, depth adjustment, filename sanitization, and notifications
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 · 145 lines · 1,888 tokens per session scan A f892f8d3dea8
DorkAgent CLAUDE.md is an instructions file published in the GitHub repository yee-yore/DorkAgent (319 stars, last pushed 12d ago), licensed MIT. It adds 1,888 tokens to every session, about $0.0094 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 instructions, from other repositories
osmedeus CLAUDE.md
Instructions for j3ssie/osmedeus, covering claude.md, build and test commands, build, test and development.
osmedeus AGENTS.md
Instructions for j3ssie/osmedeus, a project described as: A Modern Orchestration Engine for Security.
metabigor CLAUDE.md
Instructions for j3ssie/metabigor, covering metabigor - claude.md, project overview, architecture, directory structure and key design patterns.
burp-ai-agent CLAUDE.md
Claude Code instructions for six2dez/burp-ai-agent, covering project, constraints, technology stack, conventions and architecture.
burp-ai-agent AGENTS.md
AGENTS.md instructions for six2dez/burp-ai-agent, covering burp ai agent extension (kotlin) — codex instructions, non-negotiables, architecture constraints, features required and mcp integration.
ARL-Next AGENTS.md
AGENTS.md instructions for owl234/ARL-Next, covering 🤖 ai agent 核心准则, 1. 核心思维与行为红线, 2. 编码与架构规范, 3. ci/cd 与部署闭环 and 4. 文档与输出规范.