Menu
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
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Call the externally deployed DSG QUBO Policy Optimizer API to run a deterministic QUBO/Ising policy optimization. Use when a user wants to run a real optimization against the hosted service rather than the local Kotlin engine: registering/logging in for an api_key, checking account usage, and submitting an optimization run for a regulatory domain under a budget cap. Auth is an `api_key` query parameter that must come from runtime env, never from the repo. Running a real optimization may trigger solver work and may incur cost under the service's pricing tier.
Reason about deterministic QUBO/Ising policy optimization and Z3/SMT-style formal constraint verification using the Compliance-ising-z3-Deterministic engine. Use when a user asks to optimize a policy/control selection under a budget, verify logical constraints (implication, equivalence, mutual exclusion, at-least-one, cost cap), run a what-if counterfactual on budget shifts, or produce a reproducible, hash-chained compliance decision. The underlying engine is native Kotlin (no external Z3 process); constraint checks are Z3/SMT-style, implemented deterministically.
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
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 valida
Use this skill for DSG multi-source governance work that combines UI trust upgrades, action-layer permission gates, deterministic execution, marketplace/enterprise cutover, portable SaaS architecture
Apply the DSG ONE / ProofGate truth boundary and claim policy. Use when writing or reviewing any status, readiness, compliance, or capability statement destined for code, docs, commits, PRs, issues, comments, logs, or a response. Classifies each statement as verified fact / inference / pending / blocked / not verified, and flags forbidden readiness claims that require fresh evidence.
| name | dsg-action-layer-ged |
| version | 1.0.0 |
| author | DSG Team |
| license | MIT |
| description | 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 |
DSG ONE / ProofGate Control Plane is not an AI Agent framework. It is an AI Governance Control Plane — the layer that decides what Agents are allowed to do, captures cryptographic proof of every decision, and makes those decisions replayable months later.
"Cloudflare = Control Plane of the Internet. Datadog = Control Plane of Observability. DSG = Control Plane of AI Governance."
| User intent | Use this skill |
|---|---|
| "Gate this action before running it" | ✅ Yes — call gate-evaluate first |
| "Why did the AI decide X six months ago?" | ✅ Yes — use replay governance |
| "Get a compliance evidence pack for our audit" | ✅ Yes — use compliance evidence |
| "Execute this plan with a credential and conformance check" | ✅ Yes — Hermes executor |
| "What governance posture should this AI agent run with?" | ✅ Yes — runtime governance |
| "Build a generic AI feature with no governance requirement" | ❌ Out of scope |
Read the relevant reference file before answering or implementing any governance question.
| Capability | When to use | Reference |
|---|---|---|
| Deterministic Safety Gate | Before any agent action — get PASS/BLOCK/REVIEW + proof hash | <references/gate-evaluate.md> |
| Replayable Governance | Audit question: "Why did AI decide X at time T?" | <references/replay-governance.md> |
| Compliance Evidence Pack | Preparing for SOC2 / ISO27001 / EU AI Act / NIST audit | <references/compliance-evidence.md> |
| Runtime Governance | Lifecycle: Before / During / After agent execution | <references/runtime-governance.md> |
| Hermes Controlled Executor | Full Plan → Conformance Check → Credential Grant → Execute → Evidence | <references/hermes-executor.md> |
When a user asks about an AI agent action:
1. PLAN → What is the goal? What is the risk level?
2. GATE → Call POST /api/dsg/v1/gates/evaluate
→ Get gateStatus: PASS | BLOCK | REVIEW
→ Get proofHash (cryptographic evidence)
3. DECIDE → PASS → proceed to execution
REVIEW → show user the plan, require approval
BLOCK → halt, return reason + proof
4. EXECUTE → If PASS or approved REVIEW:
→ Hermes controlled executor (if credential needed)
→ Or direct execution with audit logging
5. COMMIT → POST /api/spine/execute to commit evidence
→ Runtime evidence stored in Supabase
6. REPLAY → Any future audit can replay from stored proof + policy version
| gateStatus | riskLevel | Action |
|---|---|---|
PASS | any | Proceed. Log proofHash. |
REVIEW | low–medium | Show plan to user. Require explicit approval. |
BLOCK | any | Halt. Return reason. Never proceed. |
UNSUPPORTED | low | Map to REVIEW — request human check |
UNSUPPORTED | medium–critical | Map to BLOCK — refuse execution |
UNSUPPORTED is never PASS.
riskLevel: medium or higher.UNSUPPORTED is safe — it maps to REVIEW or BLOCK, never PASS.https://tdealer01-crypto-dsg-control-plane.vercel.app
Set DSG_CONTROL_PLANE_URL to override for local or staging.
All gate/proof/compliance endpoints require:
Authorization: Bearer <DSG_API_KEY>
Obtain API key from the DSG dashboard → API Keys. Free tier: 50 evaluations/month. Upgrade at /pricing#dsg-gate.