Threatswarm: Instructions file for Claude Code

CLAUDE.md

Threatswarm CLAUDE.md is an instructions file for Claude Code from mukul975/Threatswarm. It costs 4,171 tokens per session, scanned C, original, MIT.

A cybersecurity workspace guide that defines operating rules, tool locations, and which agents handle different attack categories. It requires every target to be listed in `scope.txt` before network testing.

In plain words
What is it for?
Use it for authorized security assessments involving activities such as port scanning, web discovery, vulnerability testing, password recovery, or malware analysis.
Why use it?
It prevents security work from extending to unauthorized systems and provides a defined process for delegating reconnaissance and other testing tasks.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is mukul975/Threatswarm's own configuration. It tells Claude Code how to work on Threatswarm itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Threatswarm configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mukul975/Threatswarm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mukul975/Threatswarm/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/mukul975/Threatswarm

Made for: Claude Code.

Wrote 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.

agentmods badge for Threatswarm CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mukul975/threatswarm/claude-md.svg)](https://agentmods.dev/instructions/mukul975/threatswarm/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/mukul975/threatswarm/claude-md"><img src="https://agentmods.dev/badge/instructions/mukul975/threatswarm/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,171 This file is loaded in full into every session.
When invoked 4,171 The same file — it is already loaded in full.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.04171 $0.04171
Opus 5 $0.02086 $0.02086
Sonnet 5 $0.00834 $0.00834
Haiku 4.5 $0.00417 $0.00417

Measured 8d ago against content hash 89fe9a1e1509, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade C, and why

Threatswarm CLAUDE.md scanned grade C with 1 finding 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 8d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

8. Run `rm -rf` on evidence directories — preserve everything
CLAUDE.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cybersecurity Workspace — Master Context

Scope Enforcement (MANDATORY — ZERO EXCEPTIONS)

ALL targets MUST be listed in scope.txt before any network tool runs. The scope_check.py hook enforces this automatically on every Bash command. Add targets: IP, CIDR, or domain — one per line, comments start with #.

Tool Paths

Tool Path / Command
nmap nmap
Metasploit msfconsole, msfvenom
Nuclei nuclei
Amass amass
Subfinder subfinder
HTTPX httpx
Feroxbuster feroxbuster
SQLMap sqlmap
Hashcat hashcat
Hydra hydra
Impacket impacket-* (GetUserSPNs, secretsdump, psexec, etc.)
BloodHound bloodhound-python
CrackMapExec crackmapexec
Responder responder
Bettercap bettercap
Ghidra ghidra (headless: analyzeHeadless)
Frida frida, frida-ps
MobSF http://localhost:8000 (API)
Sliver sliver-client
Havoc ./havoc
Burp Suite burpsuite

Agent Delegation Table

Attack Category Agent When to Delegate
Port scan, service enum, web crawl recon First step on any target
Web app vulns (SQLi, XSS, LFI, SSRF) web-attacker Web ports open
AD, Kerberos, DCSync, BloodHound active-directory Domain environment
CVE exploit, get initial shell exploit (after vuln-researcher) Vulns identified
Privesc, lateral movement, persistence post-ex Shell obtained
ARP, MitM, SNMP, SMB relay network-ops Internal network
AWS, Azure, GCP, S3, IAM cloud-attacker Cloud targets
Docker, K8s, containers container-attacker Container environments
Domain intel, emails, breaches osint Passive recon phase
WiFi, WPA2, evil twin wireless-attacker Wireless testing
APK, iOS, Frida, ADB mobile-attacker Mobile app targets
REST, GraphQL, gRPC, Swagger api-attacker API surfaces
Binary RE, disasm, CTF reverse-engineer Binary analysis
Malware samples, IOCs, YARA malware-analyst Malware analysis
Phishing, pretexting, GoPhish social-engineer SE campaigns
AV bypass, AMSI, obfuscation evasion Post-access, AV present
Sliver, Havoc, MSF handler c2-operator C2 infrastructure
TLS, JWT, crypto, padding oracle crypto-attacker Crypto vulns
Firmware, IoT, UART, MQTT iot-attacker IoT/embedded devices
Hash cracking, wordlists password-attacks Hashes obtained
ATT&CK hunt, log queries threat-hunter Threat hunting
Incident triage, Volatility dfir Incident response
Hardening, Sigma, detection blue-team Defensive work
CVE research, PoC, CVSS vuln-researcher CVE investigation
CIS, PCI-DSS, NIST compliance compliance-scanner Compliance audits
Log parsing, anomaly detection log-analyst Log analysis
Pentest report generation report-writer Final deliverable

Read the full file on GitHub · 160 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. 8d ago First seen · 160 lines · 4,171 tokens per session scan C 89fe9a1e1509

Subscribe to this mod's changes

Threatswarm CLAUDE.md is an instructions file published in the GitHub repository mukul975/Threatswarm (78 stars, last pushed 4mo ago), licensed MIT. It adds 4,171 tokens to every session, about $0.0209 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens