vxcontrol/pentagi is an AI system that carries out penetration-testing tasks using multiple agents and security tools inside isolated Docker environments. It is intended for information-security professionals, researchers, and ethical hackers who automate security testing. The catalogue includes an instruction for working with PentAGI.
Borrowing it
Nothing to install: this file belongs to vxcontrol/pentagi. 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/vxcontrol/pentagi/main/CLAUDE.mdgit clone --depth 1 https://github.com/vxcontrol/pentagiWrote 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/vxcontrol/pentagi/claude-md)<a href="https://agentmods.dev/instructions/vxcontrol/pentagi/claude-md"><img src="https://agentmods.dev/badge/instructions/vxcontrol/pentagi/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/vxcontrol/pentagi/claude-md"><img src="https://agentmods.dev/badge/instructions/vxcontrol/pentagi/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 | $0.07380 | $0.07380 |
| Opus 5.5 | $0.02952 | $0.02952 |
| Sonnet 5.5 | $0.01476 | $0.01476 |
| Haiku 4.5 | $0.00738 | $0.00738 |
Grade A, and why
pentagi CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Core Interaction Rules
- English for code, comments, documentation, commit messages and identifiers.
- Password Complexity Requirements: For all password-related development (registration, password reset, API token generation, etc.), enforce the same policy in both backend and frontend — never rely on frontend validation alone. Source of truth, keep the two in sync:
backend/pkg/password/policy.go(the API validator and the installer both call it) andfrontend/src/features/authentication/password-change-form.tsx(zod schema). The policy:- Length 8–72 characters (72 bytes, the most bcrypt will hash — a longer value fails inside
bcrypt.GenerateFromPassword, after validation). - A password is valid if it is either 16+ characters (any composition), or 8–15 characters containing at least 1 lowercase letter, 1 uppercase letter, 1 number, and 1 special character from
!@#$&*.
- Length 8–72 characters (72 bytes, the most bcrypt will hash — a longer value fails inside
- Markdown is prose, not wrapped to a width. In a
.mdfile every paragraph, list item and table row is one line, and the text is split into paragraphs where the thought changes, not where a column ends — the viewer wraps it. Hard wrapping at a fixed width belongs only to comments in code.
Code Comments
The target: comment lines at 0–2% of a file of logic and about 18% of a file of type declarations; function bodies of hundreds of lines carry none, because the code says what it does.
A comment earns its place only by carrying what the code cannot show: why this decision and not the obvious one, what external constraint it works around, why the code exists at all, and — where it genuinely matters — the boundary conditions. It must help maintenance and must not cost readability.
- Never restate the code. If the sentence follows from the line under it, delete it. A doc comment that only repeats an identifier's name is noise; delete it rather than reword it. A comment that repeats the
fmt.Errorfor log message on the next line is noise too.
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 · +1 lines · +36 tokens per session 558629cd9b57
- 1mo ago Changed · +129 lines · +5,036 tokens per session 274911f11093
- 2mo ago First seen · 159 lines · 2,308 tokens per session scan A 395692e23079
pentagi CLAUDE.md is an instructions file published in the GitHub repository vxcontrol/pentagi (33,445 stars, last pushed 15d ago), licensed MIT. It adds 7,380 tokens to every session, about $0.0295 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.
pentagi CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| pentagi CLAUDE.mdvxcontrol/pentagi | Instructions file | 33k | 15d ago | MIT | A | 7,380 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |