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.
curl -O https://raw.githubusercontent.com/zebbern/zebbern-kali-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/zebbern/zebbern-kali-mcpWrote 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.
[](https://agentmods.dev/instructions/zebbern/zebbern-kali-mcp/claude-md)<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.
<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>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 | $0.08684 | $0.08684 |
| Opus 5 | $0.04342 | $0.04342 |
| Sonnet 5 | $0.01737 | $0.01737 |
| Haiku 4.5 | $0.00868 | $0.00868 |
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 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/liveroute) /healthreports an oldversion- 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.
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.
- 3d ago Changed · +27 lines · +383 tokens per session 23b419537deb
- 4d ago Changed · +95 lines · +1,425 tokens per session cfc4f3677d5e
- 5d ago First seen · 482 lines · 6,876 tokens per session scan B 9e365351ef14
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.
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.
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.
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).
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).
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.
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.