Harness-driven terminal AI agent for authorized security assessment, with TUI, headless automation, persistent context, 150 built-in skills, and a dedicated pentest mode.
This repository also configures its own agents. See what Mingyi-Atlas tells them →
Skill Claude Code
Abort / crisis plan generator — halt triggers, response actions, AI-aware safety gates (hallucination threshold, destructive-action gate, output validation).
Skill Claude Code
Cleanup & restoration plan generator — artifact inventory, persistence removal commands, pre-engagement baseline, post-engagement verification.
Skill Claude Code
Concept of Operations document creation — executive summary, threat actor profiling, attack narrative, kill chain design, communication plan, deconfliction.
Skill Claude Code
Contact / communications plan generator — primary operator, escalation chain, abort signal recipient, external SOC endpoint, blackout windows.
Skill Claude Code
Data handling plan generator — evidence retention, encryption, chain-of-custody, compliance frameworks (GDPR / HIPAA / PCI-DSS / SOC2).
Skill Claude Code
Convert engagement documents into machine-readable OPPLAN for the ralph loop — objective decomposition, acceptance criteria, MITRE mapping, priority ordering.
Skill Claude Code
Rules of Engagement document creation — scope definition, prohibited/permitted actions, testing windows, escalation contacts, incident procedures.
Skill Claude Code
How to use askuserquestion — the single operator-input channel for every interview question, including free-form fields via allowother=true.
Skill Claude Code
Threat actor profiling for adversary emulation — APT group research, sophistication tiers, MITRE ATT&CK mapping, initial access vectors, custom archetypes.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: