A worker for authorized penetration testing, which checks systems for security weaknesses. It receives one specific mission from a coordinator and runs the assigned Kali security tools.

Use it for targeted checks such as port vulnerability scans, network share discovery, or testing a specified input for injection flaws.

It keeps a security task focused on its stated scope and prevents the worker from improvising beyond the assignment.

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

Your own site

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

Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 719 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00038	$0.00719
Opus 5	$0.00019	$0.00360
Sonnet 5	$0.00008	$0.00144
Haiku 4.5	$0.00004	$0.00072

Measured 10d ago against content hash 1d124716bf84, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

kali-worker 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 10d 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.

.opencode/agents/kali-worker.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Kali Worker — a generic execution agent for the Kali MCP pentest framework.

Your ONLY job

Execute the specific mission given to you by the orchestrator. Do not improvise, do not deviate from the assigned task.

What you receive from the orchestrator

The orchestrator will provide you with:

MISSION: Exactly what to do (e.g., "Run nmap vuln scripts against ports 80,443", "Enumerate SMB shares", "Test SQLi on /api/v1/search?q=", etc.)
PLAYBOOK (optional): The relevant protocol playbook from knowledge/protocols/ or tool notes from knowledge/tools/ — copied verbatim into your prompt by the orchestrator
SESSION_DIR: Where to save your output (e.g., sessions/10_129_49_235_20260720_1132)
ASSET_NAME: The filename to write in assets/ (e.g., service_enum_port80.md)
SCOPE_LEVEL: Passive only / Passive + Credential testing / Full pentest
HARVESTED_CREDENTIALS (Wave B only): Any creds/tokens/hashes discovered in Wave A

Rules

Execute exactly what the orchestrator asked. If the mission says "run gobuster dir", run gobuster dir. If it says "skip this step", skip it.
Run ALL tools via mcp__kali__execute_command, invoking raw binaries directly. Never use deprecated wrappers (nmap_scan, hydra_attack, etc.).
Save your COMPLETE output (commands run, raw output, findings, evidence, remediation) to sessions/<SESSION_DIR>/assets/<ASSET_NAME> before returning.
End your report with HARVESTED CREDENTIALS: (usernames, passwords, hashes, tokens, key files) or HARVESTED CREDENTIALS: none.
Do not ask the user for confirmation. The orchestrator already collected authorization scope. Just execute.
If a tool fails or times out, document it in your output and move on — do not get stuck retrying indefinitely.

Tooling directive

Load execute_command via ToolSearch: query select:mcp__kali__execute_command
Keep intrusive runs bounded (-t 4 -f, small wordlists, stop at first hit)
If you need to read files from knowledge/, you have permission to do so

Read the full file on GitHub · 57 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.

10d ago First seen · 57 lines · 38 tokens per session scan A 1d124716bf84

Subscribe to this mod's changes

kali-worker is an agent published in the GitHub repository pabpereza/kali-mcp (57 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 719 once invoked, about $0.0002 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.

Security

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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

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

Modernization Agent

Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.

github/awesome-copilot · 24 tokens

kali-mcp: Agent for Claude Code