Borrowing it
Nothing to install: this file belongs to IntegSec/turbopentest-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/IntegSec/turbopentest-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/IntegSec/turbopentest-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/integsec/turbopentest-mcp/agents-md)<a href="https://agentmods.dev/instructions/integsec/turbopentest-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/integsec/turbopentest-mcp/agents-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/integsec/turbopentest-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/integsec/turbopentest-mcp/agents-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 | $0.00594 | $0.00594 |
| Opus 5 | $0.00297 | $0.00297 |
| Sonnet 5 | $0.00119 | $0.00119 |
| Haiku 4.5 | $0.00059 | $0.00059 |
Grade A, and why
turbopentest-mcp 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — TurboPentest MCP server
This file is read by coding agents (notably OpenAI Codex CLI) that don't support
the MCP "prompts" primitive. If you're Claude Code, Claude Desktop, or another
client that supports prompts, prefer calling the run_pentest, analyze_findings,
compare_pentests, and security_posture prompts directly — they contain the
same guidance as below.
What this server does
Exposes TurboPentest — AI-powered penetration testing — as MCP tools. You can launch scans, poll status, pull structured findings, download reports, and verify blockchain attestations, all from tool calls.
Setup
- Requires
TURBOPENTEST_API_KEYin the environment (see the server's own startup error if it's missing — it links to where to create one). - The target domain must be verified on the TurboPentest account first
(
turbopentest_list_domains).turbopentest_start_pentestenforces this itself and returns an error rather than launching against an unverified domain — do not try to work around that check.
Workflows
If you need to run one of the four multi-step workflows below, call the
matching turbopentest_workflow_* tool first — it returns the full
step-by-step instructions as text, which you should then follow using the
other turbopentest_* tools. Do not skip straight to guessing the steps.
- Run a full pentest → call
turbopentest_workflow_run_pentest(args:target_url,tier) - Analyze findings from a completed pentest → call
turbopentest_workflow_analyze_findings(args:pentest_id) - Compare two pentests over time → call
turbopentest_workflow_compare_pentests(args:baseline_id,current_id) - Executive security posture briefing → call
turbopentest_workflow_security_posture(no args)
Ground rules
- Never attempt to launch a pentest against a target the user hasn't
explicitly named and confirmed they own/control.
turbopentest_start_pentestwill refuse unverified domains, but don't try alternate hostnames, IPs, or spelling variants to route around that. - Long scans (
deep,blitz) can take hours. Pollturbopentest_get_pentestperiodically rather than blocking continuously, and tell the user roughly how long is left. - When presenting findings, always keep severity, CVSS, and remediation together — don't drop the remediation guidance for brevity.
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.
- today First seen · 52 lines · 594 tokens per session scan A 877dc1040cc3
turbopentest-mcp AGENTS.md is an instructions file published in the GitHub repository IntegSec/turbopentest-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 594 tokens to every session, about $0.0030 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 2026-09-10.
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).
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.
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.