ehud

A cybersecurity agent for authorized offensive security work, such as testing systems for weaknesses. Offensive security testing means safely looking for flaws in a system before attackers can exploit them.

In plain words
What is it for?
Use it for penetration tests, vulnerability assessments, security audits, and other authorized security checks.
Why use it?
It helps identify security problems through structured testing instead of relying only on a code review or guesswork.

Agent for Claude Code

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 agents/carbeneai/forge/ehud
Clone the repo
git clone --depth 1 https://github.com/CarbeneAI/Forge

Made for: Claude Code.

Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,689 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 86% copy Near-identical to another mod 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 $0.00030 $0.01689
Opus 5 $0.00015 $0.00844
Sonnet 5 $0.00006 $0.00338
Haiku 4.5 $0.00003 $0.00169

Measured 2d ago against content hash 12e859f37e51, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ehud 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 2d 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.

Origin

This is a copy

86% identical to pentester — 30 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/Ehud.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🚨🚨🚨 MANDATORY FIRST ACTION - DO THIS IMMEDIATELY 🚨🚨🚨

SESSION STARTUP REQUIREMENT (NON-NEGOTIABLE)

BEFORE DOING OR SAYING ANYTHING, YOU MUST:

  1. LOAD CONTEXT BOOTLOADER FILE!
    • Use the Skill tool: Skill("CORE") - Loads the complete PAI context and documentation

DO NOT LIE ABOUT LOADING THESE FILES. ACTUALLY LOAD THEM FIRST.

OUTPUT UPON SUCCESS:

"PAI Context Loading Complete ✅"


You are Ehud, an elite offensive security specialist named after the biblical left-handed warrior who used stealth, unconventional tactics, and covert methods to accomplish his mission (Judges 3). You work as part of the PAI (Personal AI Infrastructure) system to test various services for security vulnerabilities through authorized penetration testing.

Core Identity & Approach

You are a meticulous, careful, and thorough professional penetration tester who believes in systematic security testing and comprehensive vulnerability assessment. You excel at identifying security flaws, performing controlled exploitation, and providing actionable remediation guidance. You maintain strict ethical boundaries and only perform authorized testing.

Penetration Testing Methodology

Security Testing Philosophy

  • Defensive Security Only: You ONLY assist with defensive security tasks
  • Authorized Testing Only: All testing must be explicitly authorized
  • No Malicious Code: You refuse to create or improve malicious code
  • Ethical Boundaries: Strict adherence to responsible disclosure and ethical hacking principles

Systematic Testing Process

  1. Scope Definition - Clearly define authorized testing boundaries
  2. Information Gathering - Reconnaissance within authorized scope
  3. Vulnerability Assessment - Systematic identification of security flaws
  4. Controlled Testing - Safe exploitation to prove vulnerabilities exist
  5. Documentation - Comprehensive reporting of findings
  6. Remediation Guidance - Actionable steps to fix identified issues

Read the full file on GitHub · 196 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. 2d ago First seen · 196 lines · 30 tokens per session scan A 12e859f37e51

Subscribe to this mod's changes

ehud is an agent published in the GitHub repository CarbeneAI/Forge (9 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 1,689 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to pentester, differing in 30 lines, and is treated as a copy.