Gate AI agent actions with deterministic Z3/SMT safety checks, generate cryptographic-proof compliance evidence packs, and produce fully replayable audit trails. Integrates governance into CI/CD via GitHub Actions and browser automation for enterprise-grade AI decision control.
Run a studio-style agent control layer that turns a user goal into an explainable plan, deterministic decision flow, permission verdicts, and browser-first execution after approval. Use when the user wants to plan together first, see a separate user-facing planning pane with goals, architecture, ordered work stages, risks, and permission checkpoints, then approve the plan before live execution begins. Combines deterministic decision, a super-permission-gate, local-ops-controller rules for in-boundary authority, and browser operator behavior for real-time execution against external apps. Also covers: Deterministic Safety Gate (Z3/SMT), Replayable Governance, Compliance Evidence Pack, Runtime Governance lifecycle (Before/During/After), and Hermes Controlled Executor.
Use this skill when creating, packaging, validating, publishing, or maintaining DSG GitHub Marketplace Actions. It turns DSG control-plane, action-layer permission gates, deterministic GO/NO-GO validation, audit proof, and secure deploy checks into reusable GitHub Action products.
DSG Hybrid Agent - Multi-agent workflow executor with ROM DOM simulation + real browser fallback for DSG Control Plane
Remediation skill for shipping the DSG Governance Control Plane to the Claude Code plugin marketplace. Fixes the two remaining blockers after the marketplace.json owner merge: (1) the premature Claude.ai README claim on lines 12-13, and (2) verifying the OAuth authorization-server endpoint is live in production (not 404). Use when the user says "fix the marketplace", "ΰΉΰΈΰΉ marketplace", "deploy and verify OAuth", or "finish the marketplace listing". Trigger phrases: "fix marketplace", "ΰΉΰΈΰΉ marketplace", "verify oauth endpoint", "finish marketplace listing"
MCP server wrapper for DSG ONE control plane. Connect Claude Desktop, Cursor, or other MCP clients to the DSG runtime via standardized MCP protocol. Exposes execution gates, governance tools, agent commands, and autonomy controls. Trigger phrases: "connect to dsg", "use dsg mcp", "mcp client setup", "expose dsg tools"
External network access
Connects to servers outside your machine
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
π― ΰΈΰΉΰΈ²ΰΈΰΈ΄ΰΈͺΰΈΉΰΈΰΈΰΉ: ΰΈ₯ΰΈΰΈΰΉΰΈΰΉΰΈ«ΰΈ₯ΰΈ±ΰΈΰΈΰΈ²ΰΈ 1 ΰΈΰΈ±ΰΈ§ΰΈΰΈ±ΰΈΰΈ©ΰΈ£ ΰΈΰΉΰΈ²ΰΉΰΈΰΉΰΉΰΈ₯ΰΉΰΈ§ΰΈΰΉΰΈ²ΰΈ
βΆοΈ ΰΈΰΈΰΈ₯ΰΈΰΈ Tamper Test ΰΈͺΰΈΰΉ ΰΉΰΈ‘ΰΉΰΈΰΉΰΈΰΈΰΈͺΰΈ‘ΰΈ±ΰΈΰΈ£ | π ΰΈΰΈΉ Benchmark ΰΉΰΈΰΈ΅ΰΈ’ΰΈΰΈΰΈ₯ΰΈ²ΰΈ | Live: https://tdealer01-crypto-dsg-control-plane.vercel.app
DSG ONE ΰΈΰΈ·ΰΈΰΈΰΈ°ΰΉΰΈ£ΰΉΰΈ 1 ΰΈΰΈ£ΰΈ£ΰΈΰΈ±ΰΈ: ΰΈΰΈ΄ΰΈ‘ΰΈΰΉ Policy ΰΈ ΰΈ²ΰΈ©ΰΈ²ΰΉΰΈΰΈ’ΰΈ§ΰΉΰΈ² "ΰΈ«ΰΉΰΈ²ΰΈ‘ΰΉΰΈΰΈΰΉΰΈΰΈ΄ΰΈ 50,000" ΰΈ£ΰΈ°ΰΈΰΈΰΈΰΈ₯ΰΉΰΈΰΈ AI ΰΈΰΈ±ΰΈΰΉΰΈΰΈ‘ΰΈ±ΰΈΰΈ΄ΰΉΰΈ 11ms ΰΈΰΈ£ΰΉΰΈΰΈ‘ΰΈΰΈΰΈΰΉΰΈΰΉΰΈͺΰΈ£ΰΉΰΈ SHA-256 ΰΈΰΈ΅ΰΉΰΈΰΈ₯ΰΈΰΈ‘ΰΉΰΈ‘ΰΉΰΉΰΈΰΉΰΉΰΈ₯ΰΈ°ΰΈΰΈ³ΰΈΰΉΰΈ³ΰΉΰΈΰΉ 2 ΰΈΰΈ΅
Traditional AI systems can't be audited. They make decisions, but you can't:
DSG is policy-controlled AI that proves every decision.
Policy β Deterministic Solver β Formal Proof β Execution β Evidence
(Z3/QUBO) (SHA-256) (recorded) (auditable)
Every decision is:
A runtime governance engine for AI agents
Instead of letting AI decide directly, DSG:
Result: AI decisions that can be replayed, audited, and certified 2+ years later.
ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
β Client / Agent Request (Policy in Thai/English) β
ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
β
ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
β Policy Parser & Constraint Normalizer β
ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
β
ββββββββββββββββββ΄βββββββββββββββββ
β β
βββββββββββββββ ββββββββββββββββββββ
β Z3 Solver β β QUBO Optimizer β
β (Formal β β (NVIDIA Ising) β
β Verification) β (advisoryonly) β
βββββββββββββββ ββββββββββββββββββββ
β β
ββββββββββββββββββ¬βββββββββββββββββ
β
βββββββββββββββββββββββββββββββ
β DSG Policy Gate β
β (Decision + Proof) β
βββββββββββββββββββββββββββββββ
β
βββββββββββββββββββββββββββββββ
β Deterministic Execution β
β (Z3/QUBO result applied) β
βββββββββββββββββββββββββββββββ
β
βββββββββββββββββββββββββββββββ
β Evidence Store (Supabase) β
β + SHA-256 Merkle Ledger β
β (Auditable 2+ years) β
βββββββββββββββββββββββββββββββ
| Feature | Why It Matters |
|---|---|
| Z3 Formal Verification | Every decision has a cryptographic proof |
| Deterministic Execution | Replay any decision with same inputs β same output |
| Evidence Chain | CCVS L1-L5 compliance artifacts auto-generated |
| Policy Gateway | Define rules once, enforce everywhere (no hardcoding) |
| Audit Trail | Full SHA-256 hashed ledger, queryable back years |
| Multi-Solver | QUBO (NVIDIA Ising) + Z3 (formal), pick best fit |
npx claudepluginhub tdealer01-crypto/tdealer01-crypto-dsg-control-plane --plugin dsg-governanceAGT governance hooks and MCP tools for Claude Code sessions
DashClaw governance, integration, troubleshooting, and platform intelligence for Claude Code.
Use this agent when you need to implement AI ethics frameworks, governance policies, and responsible AI practices for B2B applications. This agent specializes in AI bias detection, ethical AI development, algorithmic transparency, and AI governance frameworks that meet enterprise trust and compliance requirements. Examples:
Achieve flow state safely with Claude Code. Auto-approves routine work, gates risky actions, hard-blocks dangerous patterns. Dual enforcement (skill + hooks), token cap for cost governance, full audit trail. Zero dependencies.
APort Agent Guardrails β security policy enforcement for every tool call. Intercepts tool use, evaluates against your passport policy, and blocks unauthorized actions.
Use this agent when you need to implement AI ethics frameworks, governance policies, and responsible AI practices for B2B applications. This agent specializes in AI bias detection, ethical AI development, algorithmic transparency, and AI governance frameworks that meet enterprise trust and compliance requirements. Examples: