hypnguyen1209/offensive-claude
Offensive security toolkit for Claude Code covering red team, exploit dev, AD attacks, EDR bypass, mobile pentest
ARCHETYPE
YOLO Cowboy
Permissions? Never heard of 'em. Ships at the speed of `--dangerously-skip-permissions`.
Copy this rig
# review before running: this installs third-party code $ claude mcp add --transport http mitm-search https://mcp.mitm.vn/mcp $ npx degit hypnguyen1209/offensive-claude/agents ./rig-offensive-claude/agents $ npx degit hypnguyen1209/offensive-claude/commands ./rig-offensive-claude/commands $ npx degit hypnguyen1209/offensive-claude/skills ./rig-offensive-claude/skills $ npx degit hypnguyen1209/offensive-claude/hooks ./rig-offensive-claude/hooks
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ claude mcp add --transport http mitm-search https://mcp.mitm.vn/mcp $ npx degit hypnguyen1209/offensive-claude/skills/active-directory-attack .claude/skills/active-directory-attack $ npx degit hypnguyen1209/offensive-claude/skills/advanced-redteam .claude/skills/advanced-redteam $ npx degit hypnguyen1209/offensive-claude/skills/ai-agent-redteam .claude/skills/ai-agent-redteam $ npx degit hypnguyen1209/offensive-claude/skills/ai-security .claude/skills/ai-security $ npx degit hypnguyen1209/offensive-claude/skills/browser-exploitation .claude/skills/browser-exploitation $ npx degit hypnguyen1209/offensive-claude/skills/cicd-supply-chain .claude/skills/cicd-supply-chain $ npx degit hypnguyen1209/offensive-claude/skills/cloud-security .claude/skills/cloud-security $ npx degit hypnguyen1209/offensive-claude/skills/coding-mastery .claude/skills/coding-mastery $ npx degit hypnguyen1209/offensive-claude/skills/container-k8s-escape .claude/skills/container-k8s-escape $ npx degit hypnguyen1209/offensive-claude/skills/crypto-analysis .claude/skills/crypto-analysis $ npx degit hypnguyen1209/offensive-claude/skills/edr-evasion .claude/skills/edr-evasion $ npx degit hypnguyen1209/offensive-claude/skills/engagement-flow .claude/skills/engagement-flow $ npx degit hypnguyen1209/offensive-claude/skills/engagement-memory .claude/skills/engagement-memory $ npx degit hypnguyen1209/offensive-claude/skills/exploit-development .claude/skills/exploit-development $ npx degit hypnguyen1209/offensive-claude/skills/finding-discipline .claude/skills/finding-discipline $ npx degit hypnguyen1209/offensive-claude/skills/incident-response .claude/skills/incident-response $ npx degit hypnguyen1209/offensive-claude/skills/initial-access .claude/skills/initial-access $ npx degit hypnguyen1209/offensive-claude/skills/keylogger-arch .claude/skills/keylogger-arch $ npx degit hypnguyen1209/offensive-claude/skills/malware-analysis .claude/skills/malware-analysis $ npx degit hypnguyen1209/offensive-claude/skills/mobile-pentest .claude/skills/mobile-pentest $ npx degit hypnguyen1209/offensive-claude/skills/network-attack .claude/skills/network-attack $ npx degit hypnguyen1209/offensive-claude/skills/opsec-discipline .claude/skills/opsec-discipline $ npx degit hypnguyen1209/offensive-claude/skills/privesc-linux .claude/skills/privesc-linux $ npx degit hypnguyen1209/offensive-claude/skills/privesc-windows .claude/skills/privesc-windows $ npx degit hypnguyen1209/offensive-claude/skills/recon-osint .claude/skills/recon-osint $ npx degit hypnguyen1209/offensive-claude/skills/red-team-ops .claude/skills/red-team-ops $ npx degit hypnguyen1209/offensive-claude/skills/reverse-engineering .claude/skills/reverse-engineering $ npx degit hypnguyen1209/offensive-claude/skills/scope-discipline .claude/skills/scope-discipline $ npx degit hypnguyen1209/offensive-claude/skills/shellcode-dev .claude/skills/shellcode-dev $ npx degit hypnguyen1209/offensive-claude/skills/threat-hunting .claude/skills/threat-hunting $ npx degit hypnguyen1209/offensive-claude/skills/threat-model-discipline .claude/skills/threat-model-discipline $ npx degit hypnguyen1209/offensive-claude/skills/using-offensive-claude .claude/skills/using-offensive-claude $ npx degit hypnguyen1209/offensive-claude/skills/vulnerability-analysis .claude/skills/vulnerability-analysis $ npx degit hypnguyen1209/offensive-claude/skills/web-pentest .claude/skills/web-pentest $ npx degit hypnguyen1209/offensive-claude/skills/windows-boundaries .claude/skills/windows-boundaries $ npx degit hypnguyen1209/offensive-claude/skills/windows-mitigations .claude/skills/windows-mitigations $ npx degit hypnguyen1209/offensive-claude/skills/wireless-rf .claude/skills/wireless-rf $ npx degit hypnguyen1209/offensive-claude/skills/writing-offensive-skills .claude/skills/writing-offensive-skills
$ curl -fsSL --create-dirs -o .claude/agents/ai-researcher.md https://raw.githubusercontent.com/hypnguyen1209/offensive-claude/main/agents/ai-researcher.md $ curl -fsSL --create-dirs -o .claude/agents/exploit-researcher.md https://raw.githubusercontent.com/hypnguyen1209/offensive-claude/main/agents/exploit-researcher.md $ curl -fsSL --create-dirs -o .claude/agents/finding-checker.md https://raw.githubusercontent.com/hypnguyen1209/offensive-claude/main/agents/finding-checker.md $ curl -fsSL --create-dirs -o .claude/agents/finding-validator.md https://raw.githubusercontent.com/hypnguyen1209/offensive-claude/main/agents/finding-validator.md $ curl -fsSL --create-dirs -o .claude/agents/network-analyst.md https://raw.githubusercontent.com/hypnguyen1209/offensive-claude/main/agents/network-analyst.md $ curl -fsSL --create-dirs -o .claude/agents/redteam-planner.md https://raw.githubusercontent.com/hypnguyen1209/offensive-claude/main/agents/redteam-planner.md $ curl -fsSL --create-dirs -o .claude/agents/reverse-engineer.md https://raw.githubusercontent.com/hypnguyen1209/offensive-claude/main/agents/reverse-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/security-reviewer.md https://raw.githubusercontent.com/hypnguyen1209/offensive-claude/main/agents/security-reviewer.md
Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.
{
"permissions": {
"deny": [
"Bash(rm -rf /)",
"Bash(rm -rf /*)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| mcp.mitm.vn · "mitm-search" | remote · remote | 2.5k |
Skills (38)
active-directory-attackadvanced-redteamai-agent-redteamai-securitybrowser-exploitationcicd-supply-chaincloud-securitycoding-masterycontainer-k8s-escapecrypto-analysisedr-evasionengagement-flowengagement-memoryexploit-developmentfinding-disciplineincident-responseinitial-accesskeylogger-archmalware-analysismobile-pentestnetwork-attackopsec-disciplineprivesc-linuxprivesc-windowsrecon-osintred-team-opsreverse-engineeringscope-disciplineshellcode-devthreat-huntingthreat-model-disciplineusing-offensive-claudevulnerability-analysisweb-pentestwindows-boundarieswindows-mitigations-bypasswireless-rfwriting-offensive-skills
Subagents (8)
| ai-researcher model: opus | AI/ML research agent — model architecture analysis, training optimization, mechanistic interpretability, safety alignment, inference optimization |
| exploit-researcher model: opus | Vulnerability research agent — identifies CVEs, finds exploit PoCs, maps attack chains, and develops custom exploitation strategies |
| finding-checker model: opus | Blind adversarial checker — given ONLY a finding artifact and its evidence (never the author's reasoning), tries to refute it and emits a structured rebuttal that drives the bounded generator↔checker |
| finding-validator model: opus | Adversarial exploitability judge — issues a PASS / KILL / DOWNGRADE / CHAIN-REQUIRED verdict on each finding, distinct from the artifact-completeness check. Tries to REFUTE every finding before accept |
| network-analyst model: opus | Deep network analysis agent — packet inspection, protocol dissection, traffic anomaly detection, IDS/IPS rule creation, firewall auditing |
| redteam-planner model: opus | Red team engagement planner — designs attack paths, C2 infrastructure, persistence strategies, and OPSEC considerations for authorized assessments |
| reverse-engineer model: opus | Binary analysis agent — disassembly, decompilation, vulnerability discovery in compiled code, firmware analysis, protocol reverse engineering |
| security-reviewer model: opus | Deep security audit agent — performs comprehensive security review of code, configs, and architecture against OWASP, MITRE ATT&CK, and CWE frameworks |
Slash commands (18)
/engage.actions/engage.c2/engage.crash/engage.cvediff/engage.deliver/engage.exploit/engage.gate/engage.init/engage.install/engage.memory/engage.pickup/engage.recon/engage.report/engage.scope/engage.scorecard/engage.status/engage.threatmodel/engage.weaponize
Permissions
deny (2)
Bash(rm -rf /)
Bash(rm -rf /*)
ask (0)
—
allow (15)
Bash(*)
Read(*)
Write(*)
Edit(*)
Glob(*)
Grep(*)
Skill(*)
Agent(*)
WebFetch(*)
WebSearch(*)
TodoWrite(*)
mcp__ida-multi-mcp__*
mcp__jadx-mcp-server__*
mcp__burp__*
mcp__caido__*
Similar rigs
Saprophytic-seattle561/reverse-skill
Map essential cybersecurity and reverse engineering skills with this structured learning path.
Skill Collector 1.7k tok ·
zhaoxuya520/reverse-skill
Reverse Engineering / Authorized Penetration Testing / Security Research Skill Router Pack AI-powered routing + On-demand toolchain bootstrapping + Self-evolving knowledge base Supports Claude Code, Kiro, Cursor, Cline, and other AI coding
Skill Collector 2.7k tok ·
Seme4eg/dotfiles
My $HOME
Pragmatist 681 tok ·
alipajand/agent-context-doctor
Audit agent context files like AGENTS.md, CLAUDE.md, .cursor/rules/*.mdc, .github/copilot-instructions.md, and prompt docs for quality, safety, contradictions, and repo alignment.
Fort Knox 1.5k tok ·