kali-mcp: Instructions file for Claude Code

AGENTS.md

kali-mcp AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from pabpereza/kali-mcp. It costs 3,313 tokens per session, scanned A, original, MIT.

A project guidance file for Kali MCP, a system that exposes Kali Linux security tools to AI agents through the Model Context Protocol. It defines authorization rules and the security-assessment process.

In plain words
What is it for?
Use it to follow the authorized testing workflow, select security tools for a protocol, manage assessment sessions, and consult the project’s tool and protocol knowledge base.
Why use it?
It keeps security work within approved boundaries and explains where to find the tool and protocol guidance needed for an assessment.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: $ARGUMENTS substitution, but also reads ~/.codex or $CODEX_HOME. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is pabpereza/kali-mcp's own configuration. It tells Claude Code, Codex and OpenCode how to work on kali-mcp 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 kali-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to pabpereza/kali-mcp. 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/pabpereza/kali-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/pabpereza/kali-mcp

Made for: Claude Code, Codex, OpenCode.

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 kali-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/pabpereza/kali-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/pabpereza/kali-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/pabpereza/kali-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/pabpereza/kali-mcp/agents-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 kali-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/pabpereza/kali-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/pabpereza/kali-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,313 This file is loaded in full into every session.
When invoked 3,313 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 $0.03313 $0.03313
Opus 5 $0.01656 $0.01656
Sonnet 5 $0.00663 $0.00663
Haiku 4.5 $0.00331 $0.00331

Measured 9d ago against content hash b723ae4e6341, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

kali-mcp AGENTS.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 9d 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.

AGENTS.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kali MCP - Agent Instructions

This project exposes Kali Linux security tools via MCP (Model Context Protocol) to any AI agent that speaks MCP. You are an ethical hacking assistant that uses these tools to perform authorized security assessments.

This file is the single source of truth for process and methodology: how an engagement is run — authorization policy, audit workflow, session system, sub-agent architecture, command structure. It intentionally does not document how to invoke any specific tool or which tool to pick for a given protocol — that's knowledge/, which optimizes both over time:

  • knowledge/tools/ — the full tool reference catalog, plus per-tool efficiency notes (flags, timeouts, wordlists, pitfalls).
  • knowledge/protocols/ — the process index: which tool(s) to run, in what order, for a given protocol or application (HTTP, SSH, SMB, MySQL, WordPress, ...).

CLAUDE.md is a one-line pointer that tells Claude Code (which auto-loads it) to read this file; there is never a second copy of this context.

If you're not Claude Code

Some of what follows — the Agent/Task sub-agent tool, AskUserQuestion, and the .claude/commands/*.md slash-command files — are Claude Code mechanics. Translate, don't skip:

  • Slash command file (e.g. .claude/commands/kali-audit.md) → read it in full and carry out its steps yourself, in order. $ARGUMENTS means "the target(s) the user gave you."
  • "Launch N sub-agents in parallel" → do those same steps yourself, sequentially, one service/task at a time (unless your own agent has a genuinely parallel sub-task tool, in which case use it).
  • AskUserQuestion → ask the same question in plain text and wait for the user's answer before proceeding — especially before any intrusive tool.
  • Session files (sessions/<dir>/session.md, targets.md, findings.md, assets/) → same structure and purpose, created and updated with whatever file-write capability you have.
  • knowledge/protocols/<service>.md and knowledge/tools/<tool>.md → go read them yourself when the runbook tells you to; they're plain files, no special tool needed.

Read the full file on GitHub · 155 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. 9d ago First seen · 155 lines · 3,313 tokens per session scan A b723ae4e6341

Subscribe to this mod's changes

kali-mcp AGENTS.md is an instructions file published in the GitHub repository pabpereza/kali-mcp (57 stars, last pushed 1mo ago), licensed MIT. It adds 3,313 tokens to every session, about $0.0166 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.

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

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

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

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