strix-proof-room

Run a Strix Governance Review (SGRF v1) on a system (/strix-governance:runtime-governance-review), a PR (/strix-governance:govern-pr), or a release (/strix-governance:release-readiness) — and wire a first governed, recorded action (/strix-governance:strix-wire). Self-host governed AI egress — a de-identifying proxy for OpenAI/Anthropic calls plus a local Claude Code prompt hook (/strix-governance:govern-ai-egress). Plugin skills are namespaced /strix-governance:<skill>. The three review lenses are advisory and run anywhere; strix-wire needs no account — Sandbox Mode auto-provisions a short-lived credential and Offline Mode makes no network calls.

7 skills

Execution control for the agents you use every day. Scan a repository for consequential actions (payments, deletes, sends, migrations, AI tool use), wrap the risky ones with Strix governance, test that the wrap governs, and check your status: /strix-personal:strix-scan, :strix-plan, :strix-apply, :strix-test, :strix-status, and :strix-wire. Receipts verify independently with npx @strixgov/verifier. The plugin renders proof; it never determines it.

2 skills · 5 commands

Independently verify Strix governance artifacts — signed evidence, approvals, quorums, agent-swarm runs, tool-gateway receipts, and CT proofs. Run the namespaced skill /strix-verifier:strix-verify or the strix_verify MCP tool; Ed25519 + JWKS, offline-capable, no Strix account. The verdict is reproducible locally or fully offline.

1 skill · 1 command · 1 MCP server · hooks

Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses

200 skills · 98 commands · 71 agents · 1 MCP server · hooks

Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF, hardcoded secrets, and 25+ other vulnerability classes.

hooks

IoT device lifecycle, telemetry anomaly detection, fleet management, and witness chain verification for Cognitum Seed hardware

5 skills · 1 command · 4 agents

Install the "AAS Security Engineer" editorial skill bundle for Claude Code.

12 skills

Duende development skills and agents for Claude Code — covering OAuth/OIDC protocols, IdentityServer, token management, ASP.NET Core authentication/authorization, BFF patterns, and secure identity architecture

24 skills · 2 agents

SAST analysis, dependency vulnerability scanning, OWASP Top 10 compliance, container security scanning, and automated security hardening

5 skills · 3 commands · 2 agents