ptai is an AI tool for authorized web application penetration testing that keeps findings as candidates until machine-controlled checks reproduce the exploit and create replayable proof. Security testers and bug bounty researchers use it with coding-agent clients or its standalone CLI to verify vulnerabilities.
Borrowing it
Nothing to install: this file belongs to 0xSteph/pentest-ai. 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/0xSteph/pentest-ai/main/AGENTS.mdgit clone --depth 1 https://github.com/0xSteph/pentest-aiWrote 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/0xsteph/pentest-ai/agents-md)<a href="https://agentmods.dev/instructions/0xsteph/pentest-ai/agents-md"><img src="https://agentmods.dev/badge/instructions/0xsteph/pentest-ai/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/0xsteph/pentest-ai/agents-md"><img src="https://agentmods.dev/badge/instructions/0xsteph/pentest-ai/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 | $0.00793 | $0.00793 |
| Opus 5.5 | $0.00317 | $0.00317 |
| Sonnet 5.5 | $0.00159 | $0.00159 |
| Haiku 4.5 | $0.00079 | $0.00079 |
Grade A, and why
pentest-ai 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent guide for pentest-ai
For AI coding agents (Claude Code, Cursor, Copilot, Codex CLI, Devin, Windsurf, Gemini CLI, Aider) and human contributors. Briefly: build, test, style, layout. Defer to README.md for product info.
Build
pip install -e .[dev]
Optional surfaces (install only what you'll touch):
pip install -e .[litellm,api,menu,browser,tracing,stealth,cloud]
Browser tests need: playwright install chromium.
Stealth crawler needs: scrapling install --force.
Test
pytest # full suite
pytest tests/test_cli.py # one file
pytest -k "name_substring" # by keyword
asyncio_mode = "auto" is set in pyproject.toml. Use pytest-asyncio patterns; do not call asyncio.run inside tests.
Lint, types, format
ruff check . # lint
ruff format . # format
mypy . # types (non-strict; see [tool.mypy] in pyproject.toml)
Pre-commit hooks: pre-commit install once, then they run on every commit.
Layout
| Path | Purpose |
|---|---|
cli/ |
ptai CLI entrypoint, menu, install wizard, MCP setup |
mcp_server/ |
FastMCP server, exposes tools to Claude Code, Cursor, etc. |
api/ |
FastAPI HTTP surface (alternative to MCP for non-MCP clients) |
engine/ |
Orchestrator, scope, auth, findings DB, telemetry, HITL, playbooks |
agents/ |
BaseAgent orchestrator classes (18 dirs under agents/) |
tools/ |
Wrappers — all of them in tools/registry.py |
playbooks/ |
YAML multi-step engagement playbooks |
tests/ |
pytest suite |
benchmarks/ |
reproducible solve-rate measurements |
docs/ |
user-facing documentation |
Conventions
- Python ≥ 3.10. Tested on 3.10 – 3.14 (
requires-python = ">=3.10,<3.15"). - Add tests for new code; mirror module structure in
tests/. - New tool wrappers register in
tools/registry.py(there are no per-category packages undertools/). - New agents subclass
agents/base.py:BaseAgent. - 160-char line length (
ruffconfig). - No secrets in code or tests.
.env*is gitignored.
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.
- 1mo ago Changed · -30 tokens per session aed38a4a9ff8
- 1mo ago First seen · 78 lines · 823 tokens per session scan A 5c846bc2059b
pentest-ai AGENTS.md is an instructions file published in the GitHub repository 0xSteph/pentest-ai (1,780 stars, last pushed 18d ago), licensed MIT. It adds 793 tokens to every session, about $0.0032 per session on Opus 5.5. 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.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.