pentagi CLAUDE.md

A set of coding-agent instructions for PentAGI, an AI-assisted platform for automated security testing, covering project rules, development commands, and backend work.

In plain words
What is it for?
Use it when working on PentAGI, especially authentication, password validation, frontend/backend changes, or backend development commands.
Why use it?
It gives agents the project's required conventions and safety-related implementation rules before they modify the codebase.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/vxcontrol/pentagi/claude-md
Clone the repo
git clone --depth 1 https://github.com/vxcontrol/pentagi
Per session 2,308 This file is loaded in full into every session.
When invoked 2,308 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found 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 $0.02308 $0.02308
Opus 5 $0.01154 $0.01154
Sonnet 5 $0.00462 $0.00462
Haiku 4.5 $0.00231 $0.00231

Measured 2d ago against content hash 395692e23079, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

CLAUDE.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 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

  1. Always use English for all interactions, responses, explanations, and questions with users.
  2. 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/server/models/init.gostrongPasswordValidatorString and frontend/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 !@#$&*.

Project Overview

PentAGI is an automated security testing platform powered by AI agents. It runs autonomous penetration testing workflows using a multi-agent system (Researcher, Developer, Executor agents) that coordinates LLM providers, Docker-sandboxed tool execution, and a persistent vector memory store.

The application is a monorepo with:

  • backend/ — Go REST + GraphQL API server
  • frontend/ — React + TypeScript web UI
  • observability/ — Optional monitoring stack configs

Build & Development Commands

Backend (run from backend/)

go mod download                              # Install dependencies
go build -trimpath -o pentagi ./cmd/pentagi  # Build main binary
go test ./...                                # Run all tests
go test ./pkg/foo/... -v -run TestName       # Run specific test
golangci-lint run --timeout=5m               # Lint

# Code generation (run after schema changes)
go run github.com/99designs/gqlgen --config ./gqlgen/gqlgen.yml  # GraphQL resolvers
swag init -g ../../pkg/server/router.go -o pkg/server/docs/ --parseDependency --parseInternal --parseDepth 2 -d cmd/pentagi  # Swagger docs

Read the full file on GitHub · 159 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. 2d ago First seen · 159 lines · 2,308 tokens per session scan A 395692e23079

Subscribe to this mod's changes

pentagi CLAUDE.md is an instructions file published in the GitHub repository vxcontrol/pentagi (22,176 stars, last pushed 26d ago), licensed MIT. It adds 2,308 tokens to every session, about $0.0115 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 2026-08-30.