Plugin Claude Code
Proteus plugins for Claude Code and Codex focused on structured, exploitability-driven vulnerability research.
Plugin Claude Code
Proteus plugins for Claude Code and Codex focused on structured, exploitability-driven vulnerability research.
Agent
MUST BE USED for Proteus component-level review fronts where a bounded module, component, or primitive needs detailed security inspection.
Agent
MUST BE USED after initial Proteus gates pass to build realistic PoC labs, manual repro steps, negative controls, and triage-ready report drafts.
Agent
MUST BE USED for Proteus fuzzing, edge-case, parser, canonicalization, cache-key, or anomaly-matrix fronts.
Agent
MUST BE USED only when a Proteus branch already has concrete signal and needs exploit-development, bypass, chaining, reliability, or impact-proof work.
Agent
MUST BE USED before any Proteus report-grade claim to verify docs, tests, contracts, advisories, issues, changelogs, public-known behavior, and timeline.
Agent
MUST BE USED for Proteus macro or chaining analysis where separate primitives may combine into a realistic exploit path.
Agent
MUST BE USED for Proteus runtime, adapter, deployment, build, Docker, WSL, native, or environment-divergence fronts.
Agent
MUST BE USED before any Proteus report-grade claim to refute, downgrade, or kill candidates through adversarial review.
Command
Run Proteus continuous vulnerability research for the current target.
Skill Claude CodeCodex
Develop non-obvious Proteus exploit chains from primitives, side effects, state drift, and component coupling.
Skill Claude CodeCodex
Compress Proteus campaign or round state into a concise checkpoint with facts, killed paths, pivots, and next moves.
Skill Claude CodeCodex
Map a codebase for Proteus research through architecture, dataflow, trust boundaries, invariants, and high-ROI branch material.
Skill Claude CodeCodex
Design calibrated Proteus fuzzing and differential probes that learn input behavior instead of spraying generic payloads.
Skill Claude CodeCodex
Build realistic Proteus PoC plans, labs, negative controls, and exploitability evidence for concrete candidates.
Skill Claude CodeCodex
Gather Proteus security intelligence for known status, timelines, advisories, changelogs, docs, and duplicate risk.
Skill Claude CodeCodex
Conduct authorized Proteus web research with campaign memory, chaining, fuzzing, intel, and PoC heuristics.
Skill Claude CodeCodex
Coordinate Proteus continuous vulnerability research with memory, campaigns, delegation, validation gates, and report-grade discipline.
Plugin Claude Code
A plugin for Claude Code and Codex that coordinates structured, continuous vulnerability research with memory, strategy, and realistic validation.
MCP server Claude CodeCodexCursor +2
MCP server "proteus" as configured in Vyntra-Research/Proteus. Runs ${CLAUDE_PLUGIN_ROOT}/scripts/proteus-mcp.cjs with node.
Skill Claude CodeCodex
Develop non-obvious exploit chains from concrete primitives, side effects, trust-boundary drift, state transitions, component coupling, and capability amplification. Use when a Proteus branch needs creative offensive reasoning beyond the obvious direct bug path.
Skill Claude CodeCodex
Compress Proteus campaign or round state after meaningful progress, preserving confirmed facts, killed paths, pivots, branch scores, learned heuristics, unresolved blockers, and the next high-ROI move.
Skill Claude CodeCodex
Operate as a secondary OpenCode-backed Proteus Chimera agent with coordinator-controlled scope, communication, snapshots, labs, and permissions.
Skill Claude CodeCodex
Perform deep offensive codebase research for Proteus by mapping architecture, dataflow, trust boundaries, invariants, side effects, recent change risk, and high-ROI branch material. Use when Codex must understand a codebase before chaining, fuzzing, Cicada, or PoC work.