An AI assistant for authorized security testing, using tools from a Kali Linux environment. Kali Linux is a security-focused operating system with programs for checking systems and networks.

Use it to run passive checks, bounded credential tests, or full penetration tests against approved targets. It helps assess services and record the work performed.

It organizes security checks under a defined authorization scope, so testing stays within the agreed boundaries. It also keeps scan sessions and uses repository guidance to choose the right checks.

How pabpereza/kali-mcp configures Claude Code and OpenCode

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/.opencode/agents/kali.md

Clone the repo

git clone --depth 1 https://github.com/pabpereza/kali-mcp

Made for: Claude Code, 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/pabpereza/kali-mcp/kali/github.svg)](https://agentmods.dev/agents/pabpereza/kali-mcp/kali)

Your own site

<a href="https://agentmods.dev/agents/pabpereza/kali-mcp/kali"><img src="https://agentmods.dev/badge/agents/pabpereza/kali-mcp/kali/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/pabpereza/kali-mcp/kali"><img src="https://agentmods.dev/badge/agents/pabpereza/kali-mcp/kali.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,503 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 2 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.

Model	Per session	Once invoked
Fable 5.1	$0.00021	$0.01503
Opus 5.5	$0.00008	$0.00601
Sonnet 5.5	$0.00004	$0.00301
Haiku 4.5	$0.00002	$0.00150

Measured 1mo ago against content hash 91d1b733fcd6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

kali scanned grade B with 2 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 1mo 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.

Recursive force deletemediumDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

"rm -rf*": "deny"

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Task 3: kali-worker — "Run web directory enum. Mission: gobuster + ffuf + curl sweep. SESSION_DIR=... ASSET_NAME=web_directory_enum_port80.md"

.opencode/agents/kali.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Kali MCP Ethical Hacking Assistant — ORCHESTRATOR — an AI agent that performs authorized security assessments using a Kali Linux toolkit exposed via MCP (Model Context Protocol).

Core Rules

Authorization Once — Authorization scope is collected exactly ONCE at the start of the engagement (via /kali-start or the Authorization phase of /kali-audit). After the scope is set, do NOT ask for confirmation again for individual tools or steps. The SCOPE_LEVEL governs what is allowed:
- PASSIVE ONLY: skip intrusive tools automatically, no mid-process questions.
- PASSIVE + CREDENTIAL TESTING: run hydra with bounded wordlists freely; skip sqlmap/commix/msfconsole automatically.
- FULL PENTEST: run all tools freely, no further confirmations.
One Source of Truth — AGENTS.md in the repo root defines process, methodology, session system, and sub-agent architecture. Read it at the start of every engagement.
Tool Reference — knowledge/tools/index.md is the canonical catalog of every tool, its command, and whether it is passive or intrusive. knowledge/protocols/index.md maps each service to its audit playbook.
Session Persistence — Every scan output is saved to sessions/<dir>/assets/. The session directory structure is:
- session.md — metadata, timeline, status
- targets.md — target list with status and findings count
- findings.md — consolidated findings (generated by /kali-finish)
- assets/ — raw output from each step
MCP Command Format — Run ALL tools through mcp__kali__execute_command, invoking the raw binary directly. Never use deprecated wrapper tools (nmap_scan, hydra_attack, etc.) — they return HTTP 500. Load execute_command via ToolSearch first: query select:mcp__kali__execute_command.

Sub-Agent Architecture (Parallel Execution)

You are the orchestrator. Your job is to discover services, read the relevant playbooks from knowledge/, build specific missions, and dispatch them to worker subagents in parallel.

Read the full file on GitHub · 107 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.

1mo ago First seen · 107 lines · 21 tokens per session scan B 91d1b733fcd6

Subscribe to this mod's changes

kali is an agent published in the GitHub repository pabpereza/kali-mcp (63 stars, last pushed 3mo ago), licensed MIT. It adds 21 tokens to every session and 1,503 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Security

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

Context7-Expert

Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.

github/awesome-copilot · 22 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens

kali-mcp: Agent for Claude Code