pentest-mcp-server: Instructions file for Claude Code

AGENTS.md

pentest-mcp-server AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from cyanheads/pentest-mcp-server. It costs 5,192 tokens per session, scanned A, a copy of obsidian-mcp-server AGENTS.md, Apache-2.0.

Developer instructions for the pentest-mcp-server, an offline server for authorized penetration testing and related research. They describe its tools, framework, runtime, and coding rules.

In plain words
What is it for?
Use them when developing or reviewing this server, especially when adding tools, handling errors, logging, or maintaining its embedded methodology data.
Why use it?
They give contributors the project-specific rules needed to change the server consistently and safely, including required reminders about authorized use.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: Claude Code plugin machinery, but also the file is AGENTS.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

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

Reuse

Borrowing it

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

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 pentest-mcp-server AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cyanheads/pentest-mcp-server/agents-md.svg)](https://agentmods.dev/instructions/cyanheads/pentest-mcp-server/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/cyanheads/pentest-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/cyanheads/pentest-mcp-server/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 5,192 This file is loaded in full into every session.
When invoked 5,192 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 73% copy Near-identical to another mod 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 $0.05192 $0.05192
Opus 5 $0.02596 $0.02596
Sonnet 5 $0.01038 $0.01038
Haiku 4.5 $0.00519 $0.00519

Measured 6d ago against content hash d5f6ffafc9f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

pentest-mcp-server 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 6d 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.

Origin

This is a copy

73% identical to obsidian-mcp-server AGENTS.md — 355 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

AGENTS.md · 356 lines

How it starts

The opening of the file, as written. The whole thing — 356 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Developer Protocol

Server: pentest-mcp-server Version: 0.1.8 Framework: @cyanheads/mcp-ts-core ^0.12.3 Engines: Bun ≥1.3.0, Node ≥24.0.0 MCP SDK: @modelcontextprotocol/server / @modelcontextprotocol/client ^2.0.0 (via framework) Zod: ^4.4.3

Read the framework docs first: node_modules/@cyanheads/mcp-ts-core/CLAUDE.md contains the full API reference — builders, Context, error codes, exports, patterns. This file covers server-specific conventions only.


Core Rules

  • Logic throws, framework catches. Tool handlers are pure — throw on failure, no try/catch. Plain Error is fine; the framework catches, classifies, and formats. Use error factories (notFound(), validationError(), etc.) when the error code matters.
  • Use ctx.log for request-scoped logging. No console calls.
  • Stateless by design. All tools read from embedded data initialized at startup. No ctx.state writes, no external API calls, no side effects.
  • authorized_use_reminder is never empty. Every tool that returns methodology or payload content must include this required field. The format() function renders it as the first line of content[]. Enforce at the type level — the schema makes it required, not optional.
  • Detection + mitigation are required, not optional. Every technique, finding, and payload object in the output schema has non-optional detection and mitigation fields. Do not relax them.
  • Payloads are annotated templates, not live exploits. The pentest_generate_payloads tool returns illustrative templates with context annotations. Never include live weaponized strings with no pedagogical framing.
  • Secrets in env vars only — never hardcoded.
  • Close the loop on issues. When implementing work tracked by a GitHub issue, comment on the issue with what landed and close it. Do both — a comment without a close leaves stale issues open; a close without a comment leaves no record of what shipped. The comment is for future readers — state the concrete changes, not the conversation that produced them.

Read the full file on GitHub · 356 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. 6d ago First seen · 356 lines · 5,192 tokens per session scan A d5f6ffafc9f7

Subscribe to this mod's changes

pentest-mcp-server AGENTS.md is an instructions file published in the GitHub repository cyanheads/pentest-mcp-server (1 stars, last pushed 15d ago), licensed Apache-2.0. It adds 5,192 tokens to every session, about $0.0260 per session on Opus 5. A static security scan graded it A with 0 findings. It is 73% identical to obsidian-mcp-server AGENTS.md, differing in 355 lines, and is treated as a copy.

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 · 5,182 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