CLAUDE.md · projectdiscovery/nuclei
CLAUDE.md from projectdiscovery/nuclei: 86 lines covering Project Overview, Development Commands, Architecture Overview, Template Development and more.
Template by projectdiscovery
Chalk Labs
Need help deploying CLAUDE.md · projectdiscovery/nuclei?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code. Read the repository before you give any tool access to your data.
curl -fsSL https://raw.githubusercontent.com/projectdiscovery/nuclei/dev/CLAUDE.md -o CLAUDE.md
Read it and adapt it to your project before use.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: prompt-engineering, code-generation
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
What's in it
A CLAUDE.md file: project memory Claude Code loads at the start of every session.
- For
- Claude Code
- Length
- 86 lines
- File
CLAUDE.md
Sections
- Project Overview
- Development Commands
- Architecture Overview
- Template Development
- Key Directories
First lines (shown under the repo's MIT license)
# CLAUDE.md This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository. ## Project Overview Nuclei is a modern, high-performance vulnerability scanner built in Go that leverages YAML-based templates for customizable vulnerability detection. It supports multiple protocols (HTTP, DNS, TCP, SSL, WebSocket, WHOIS, JavaScript, Code) and is designed for zero false positives through real-world condition simulation. ## Development Commands ### Building and Testing - `make build` - Build the main nuclei binary to ./bin/nuclei - `make test` - Run unit tests with race detection - `make integration` - Run the native integration suite via `go test -tags=integration ./internal/tests/integration` - `make functional` - CI-only functional suite entry point - `make vet` - Run go vet for code analysis - `make tidy` - Clean up go modules ### Validation and Linting - `make template-validate` - Validate nuclei templates using the built binary - `go fmt ./...` - Format Go code - `go vet ./...` - Static analysis ### Development Tools - `make devtools-all` - Build all development tools (bindgen, tsgen, scrapefuncs) - `make jsupdate-all` - Update JavaScript bindings and TypeScript definitions - `make docs` - Generate documentation - `make memogen` - Generate memoization code for JavaScript libraries ### Testing Specific Components - Run single test: `go test -v ./pkg/path/to/package -run TestName` - Integration tests are in `internal/tests/integration/` and run via `go test -tags=integration ./internal/tests/integration` ## Architecture Overview ### Core Components - **cmd/nuclei** - Main CLI entry point with flag parsing and configuration - **internal/runner** - Core runner that orchestrates the entire scanning process - **pkg/core** - Execution engine with work pools and template clustering - **pkg/templates** - Template parsing, compilation, and management - **pkg/protocols** - Protocol implementations (HTTP, DNS, Network, etc.) - **pkg/operators** - Matching and extraction logic (matchers/extractors) - **pkg/catalog** - Template discovery and loading from disk/remote sources ### Protocol Architecture Each protocol (HTTP, DNS, Network, etc.) implements: - Request interface with Compile(), ExecuteWithResults(), Match(), Extract() methods - Operators embedding for matching/extraction functionality - Protocol-specific request building and execution logic ### Template System - Templates are YAML files defining vulnerability detection logic - Compiled into executable requests with operators (matchers/extractors) - Support for workflows (multistep template execution) - Template clustering optimizes identical requests across multiple templates ### Key Execution Flow 1. Template loading and compilation via pkg/catalog/loader 2. Input provider setup for targets 3. Engine creation with work pools for concurrency 4. Template execution with result collection via operators 5. Output writing and reporting integration ### JavaScript Integration - Custom JavaScript runtime for code protocol templates - Auto-generated bindings in pkg/js/generated/ - Library implementations in pkg/js/libs/ - Development tools for binding generation in pkg/js/devtools/ ## Template Development - Templates located in separate nuclei-templates repository - YAML format with info, requests, and operators sections - Support for multiple protocol types in single template - Built-in DSL functions for dynamic content generation - Template validation available via `make template-validate` ## Key Directories - **lib/** - SDK for embedding nuclei as a library - **examples/** - Usage examples for different scenarios - **internal/tests/integration/** - Native integration suite and owned testdata for harness coverage - **internal/tests/functional/** - CI-only native functional comparison suite and testcase assets - **pkg/fuzz/** - Fuzzing engine and DAST capabilities - **pkg/input/** - Input processing for various formats (Burp, OpenAPI, etc.) - **pkg/reporting/** - Result export and issue tracking integrations See SECURITY_CONTEXT.md for this repo's known vulnerabilities and recurring weak spots. Check it before writing or reviewing security-sensitive code.
Signals
- Stars
- 32,284
- Forks
- 3,941
- Open issues
- 62
- Last commit (this folder)
- Sep 1, 2026 (1 month ago)
- Last release
- Aug 8, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/projectdiscovery/nuclei
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get CLAUDE.md · projectdiscovery/nuclei running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
CLAUDE.md · projectdiscovery/nuclei. Agent Mart. https://agentmart.dev/templates/projectdiscovery-nuclei-claude-md (last updated 2026-10-24)