AIagentPRO78

Cybersec 10000 — Security skill for Claude Code

Security community

40-agent, ~10,163-dimension security analysis swarm (static + live ops) with a scored 46-chain exploit planner and Jev (TypeSafe System One) decisioning.

How to install Cybersec 10000

This entry records only its repository, not the path inside it, so there is no exact command to give. Open AIagentPRO78/cybersec-10000 and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Cybersec 10000 does

40-agent, ~10,163-dimension security analysis swarm (static + live ops) with a scored 46-chain exploit planner and Jev (TypeSafe System One) decisioning. Built and verified; source available on request.

Alternatives in Security

Exploit 2.3k ★
/chain — Build an A→B→C exploit chain for higher severity and payout 927 ★
Engage.Exploit — Execute Phase 4 - Exploitation and Access Establishment 348 ★

README

cybersec-10000 — a 40-agent security analysis swarm

A Claude Code plugin I designed and built: **40 specialized security agents covering ~10,163 security dimensions**, spanning static code/architecture audit and live offensive operations, orchestrated by a scored exploit-chain planner with a judgment layer on the live-operations path. Currently at **v1.4.2**, actively maintained.

**This repo is a public showcase, not the source.** The plugin source is private and shared on request — contact me on GitHub: [@AIagentPRO78](https://github.com/AIagentPRO78). See [Requesting access](#requesting-access).

At a glance


Version	v1.4.2 — shipped to `main` (merged, not a feature branch)
Agents	40 — 20 static analysis · 16 live operations · 4 specialist
Dimensions	~10,163 — 5,076 static · 3,087 live · 2,000 specialist
Exploit chains	46 named chains across 9 categories
Capabilities	133 reusable capability tags
Frameworks mapped	40+ (OWASP, MITRE ATT&CK/ATLAS, NIST, PCI DSS 4.0, ISO 27001:2022, CIS, …)
Tests	502 passed (`pytest`, chain-planner)
License	MIT — source shared on request

1. Architecture

![cybersec-10000 architecture](architecture.svg)

Four slash commands (`/cybersec-scan`, `/chain-plan`, `/chain-run`, `/war-room`) feed a `chain-planner` orchestration layer that scores 46 pre-built exploit chains against a target (`payout_prior × applicability × freshness_decay`) and fans out to three agent tiers. Static-analysis agents are read-only and safe to run anywhere; live-operations agents execute exclusively against a dedicated attack box (a Vultr VPS reached over WireGuard), never from the operator's own machine.