zebbern-kali-mcp: Instructions file for Claude Code

CLAUDE.md

zebbern-kali-mcp CLAUDE.md is an instructions file for Claude Code from zebbern/zebbern-kali-mcp. It costs 8,684 tokens per session, scanned B, original, MIT.

A set of repository instructions for the zebbern-kali-mcp project, which provides tools through the Model Context Protocol. It documents how Python package releases differ from Docker image releases and how local images can become outdated.

In plain words
What is it for?
Use it when reviewing changes, preparing releases, rebuilding or checking Docker images, and deciding whether a change belongs in the Python package or container release.
Why use it?
It prevents releasing the wrong artifact or assuming that publishing one track updates the other. It also helps diagnose problems caused by an old local Docker image.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md.

This is zebbern/zebbern-kali-mcp's own configuration. It tells Claude Code how to work on zebbern-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 zebbern-kali-mcp configures →

Reuse

Borrowing it

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

Made for: Claude Code.

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 zebbern-kali-mcp CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/zebbern/zebbern-kali-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/zebbern/zebbern-kali-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 8,684 This file is loaded in full into every session.
When invoked 8,684 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.08684 $0.08684
Opus 5 $0.04342 $0.04342
Sonnet 5 $0.01737 $0.01737
Haiku 4.5 $0.00868 $0.00868

Measured 3d ago against content hash 23b419537deb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

zebbern-kali-mcp CLAUDE.md 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 3d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

`sudo nmap`, `/usr/bin/nmap` and `echo x | waybackurls` all missed their entry

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

`output_file`, call `subprocess.run` directly rather than `execute_command`, and
CLAUDE.md · 604 lines

How it starts

The opening of the file, as written. The whole thing — 604 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Operational notes for this repo. Everything here is a mistake that has actually been made, not general advice.

Two release tracks, and they are not the same

The wheel ships only mcp_server.py and mcp_tools/* (pyproject.toml py-modules / packages.find). Everything under zebbern-kali/ ships in the Docker image instead, and reaches users when docker-publish.yml rebuilds — not when you publish to PyPI.

Before proposing a release, check which track the change is on:

git diff --name-only <last-tag>..main

A change under zebbern-kali/ does not justify a PyPI bump, and a PyPI release does not deliver it. This has been misread once already — a proposed release turned out to contain nothing but a comment.

The local backend image goes stale silently

ghcr.io/zebbern/zebbern-kali-mcp:latest moves on every docker-publish run, which triggers on any push to main touching Dockerfile, .dockerignore, docker/**, docker-compose*.yml, entrypoint.sh, requirements.txt or zebbern-kali/**. A local copy pulled earlier keeps serving, and the symptoms never look like staleness:

  • container reports unhealthy (an old image predating the /live route)
  • /health reports an old version
  • tests pass against bits nobody ships
docker compose pull && docker compose up -d --force-recreate
docker buildx imagetools inspect ghcr.io/zebbern/zebbern-kali-mcp:latest   # remote
docker image inspect ghcr.io/zebbern/zebbern-kali-mcp:latest --format '{{index .RepoDigests 0}}'

Compare those two digests before trusting anything the backend says. This has happened three times.

Targeting the host from inside the container

Inside the container 127.0.0.1 is the container's own loopback. The host (and anything published on it, e.g. a crAPI lab on 8888) is reachable as host.docker.internal. Scanning 127.0.0.1 finds an empty container and looks exactly like a broken MCP server.

Services on another compose network that are not host-published (crAPI's crapi-identity:8080, crapi-community:6060) need the Kali container attached to that network.

Read the full file on GitHub · 604 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. 3d ago Changed · +27 lines · +383 tokens per session 23b419537deb
  2. 4d ago Changed · +95 lines · +1,425 tokens per session cfc4f3677d5e
  3. 5d ago First seen · 482 lines · 6,876 tokens per session scan B 9e365351ef14

Subscribe to this mod's changes

zebbern-kali-mcp CLAUDE.md is an instructions file published in the GitHub repository zebbern/zebbern-kali-mcp (46 stars, last pushed 3d ago), licensed MIT. It adds 8,684 tokens to every session, about $0.0434 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.

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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,737 tokens