The hivemind for AI coding agents — persistent team context recorded once and recalled across agents, machines, and teammates.
Agent Claude Code
BYOK (Bring-Your-Own-Key) and OAuth token security expert. Deep on cross-platform OS keychain integration (macOS Keychain, Linux Secret Service / kwallet / gnome-keyring, Windows Credential Manager), token caching tradeoffs, env-var hygiene, accidental-commit prevention beyond gitleaks, sub-process credential leakage…
Agent Claude Code
Model Context Protocol (MCP) security expert. Deep on tool dispatch validation, schema enforcement, server impersonation defenses, transport (stdio/SSE) trust assumptions, and the emergent attack surface that opens when LLM output drives tool execution. Use PROACTIVELY when reviewing MCP server code (internal/mcp/ in…
Agent Claude Code
Expert in OpenGrep (FOSS Semgrep fork) and Semgrep rule authoring. Writes precise patterns, taint-tracking rules, framework-specific entry-point detectors, and metavariable-based queries. Knows the YAML rule format inside out and the cross-function taint analysis OpenGrep restored after the late-2024 Semgrep CE…
Agent Claude Code
Adversarial security expert. Thinks like an attacker — chains primitives into exploits, finds auth bypass, IDOR, SSRF, deserialization, race conditions, business-logic abuse. Use PROACTIVELY when reviewing new auth/authz code, public endpoints, mutation handlers, or anything touching the trust boundary. Use when…
Agent Claude Code
Software supply-chain security expert. Deep on Socket.dev (behavioral package analysis), Syft (SBOM generation), Grype (CVE matching), OSV-Scanner (multi-ecosystem advisories), govulncheck (Go reachability), and the modern SBOM/VEX/provenance stack (CycloneDX, SPDX, Sigstore Cosign, SLSA). Use PROACTIVELY when…
Agent Claude Code
Threat-modeling specialist using STRIDE, PASTA, and LINDDUN. Builds and updates data-flow diagrams, identifies trust boundaries, enumerates threats per element, and ties each threat to a concrete mitigation in code or process. Use PROACTIVELY when designing a new feature, evolving an existing system, authoring or…
Agent
Review schema changes and migrations with team patterns.
Agent
The hivemind for AI coding agents — persistent team context recorded once and recalled across agents, machines, and teammates.