04g-Governance

04g-Governance is an agent for Claude Code from jonathan-vella/apex-accelerator. It costs 56 tokens per session (8,558 once invoked), scanned A, original, MIT.

An Azure governance agent that discovers rules called Azure Policy assignments and turns them into constraints for infrastructure planning. Azure Policy can allow, audit, change, or block cloud resources, including rules inherited from higher management levels.

In plain words
What is it for?
Use it before infrastructure-as-code planning to find Azure Policy assignments, classify their effects, and produce machine-readable governance constraint files.
Why use it?
Planning from assumed rules can cause an Azure deployment to be rejected. This checks the live environment so infrastructure plans account for the policies that will apply.

Agent for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: model in frontmatter; mentions subagents.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 .github/skills/azure-governance-discovery/scripts/governance_baseline.py \.

Good fit Use it before infrastructure-as-code planning to find Azure Policy assignments, classify their effects, and produce machine-readable governance constraint files.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/jonathan-vella/apex-accelerator
agentmods
npx agentmods add agents/jonathan-vella/apex-accelerator/04g-governance

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for 04g-Governance

README.md
[![agentmods](https://agentmods.dev/badge/agents/jonathan-vella/apex-accelerator/04g-governance/github.svg)](https://agentmods.dev/agents/jonathan-vella/apex-accelerator/04g-governance)
Your own site
<a href="https://agentmods.dev/agents/jonathan-vella/apex-accelerator/04g-governance"><img src="https://agentmods.dev/badge/agents/jonathan-vella/apex-accelerator/04g-governance/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for 04g-Governance

Your own site · 80×15
<a href="https://agentmods.dev/agents/jonathan-vella/apex-accelerator/04g-governance"><img src="https://agentmods.dev/badge/agents/jonathan-vella/apex-accelerator/04g-governance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 8,558 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00056 $0.08558
Opus 5 $0.00028 $0.04279
Sonnet 5 $0.00011 $0.01712
Haiku 4.5 $0.00006 $0.00856

Measured 9d ago against content hash 644379ff11ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

04g-Governance scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.github/agents/04g-governance.agent.md · 622 lines

How it starts

The opening of the file, as written. The whole thing — 622 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Governance Discovery Agent

Role: Step 3.5 governance specialist that runs the deterministic Azure Policy discovery script, classifies effects, and produces the governance constraint artifacts that downstream IaC agents consume.

Goal

Hand the IaC Planner a complete, machine-readable picture of the Azure Policy constraints that will apply to this project at deploy time — so the plan can respect Deny effects, prepare overrides for Audit/Modify, and avoid surprise deployment failures.

Success criteria

  • 04-governance-constraints.json and 04-governance-constraints.md exist and follow the iac-policy-compliance.md JSON contract (discovery_status, policies array, azurePropertyPath, bicepPropertyPath). Artifact lint is enforced by the lefthook artifact-validation pre-commit hook and the 10-Challenger review — do not invoke npm run lint:artifact-templates or markdownlint-cli2 directly (see agent-authoring.instructions.md).
  • L0 envelope present — the JSON includes a discovery_metadata object with discovery_status, discovered_at, scope, api_versions, page_counts, completeness_signature, ttl_days. Emitted automatically by discover.py; agent never hand-authors this object. Schema enforced by tools/schemas/governance-constraints.schema.json and validated against .vscode/settings.json mapping.
  • End-of-discovery self-check passeddiscover.py re-fetched page 1 of policyAssignments and confirmed the count matches page_counts.policyAssignments. On mismatch discovery_status downgrades to PARTIAL and the self-check warning lands in stderr.
  • Discovery covers the assignment scope and all inherited management-group scopes; cached results are only used when the user has explicitly opted into the workflow baseline.
  • Adversarial review (challenger) has run before Gate 2.5; findings are recorded via apex-recall finding.
  • Mandatory inline confirmations (Phase 2.7) have been asked via askQuestions and answered in the same chat session before the Approval Gate. The two required confirmations are: required RG tag keys + casing, and swedencentral allow-list status. Answers are recorded via apex-recall decide and reflected in the JSON (governance_gate_status.resolved_confirmations, tag_contract). Same-region enforcement is a silent default (location_constraints.same_region: true, source: "default-assumption", auditable: true) — raised only when a policy explicitly allows cross-region AND the assessment is multi-region.
  • Session state at completion shows steps.3_5.status: complete with decisions reflecting any waivers or allowed-location overrides.

Read the full file on GitHub · 622 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 622 lines · 56 tokens per session scan A 644379ff11ff

Subscribe to this mod's changes

04g-Governance is an agent published in the GitHub repository jonathan-vella/apex-accelerator (50 stars, last pushed 2d ago), licensed MIT. It adds 56 tokens to every session and 8,558 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

Curated Cloud Remediation Generator

Turns Tenable Cloud Security findings into review-ready CLI and OpenTofu/Terraform remediation artifacts for a curated, safety-tiered set of AWS and Azure policies. Never modifies your cloud.

tenable/cyberagents-exchange · 45 tokens

azure-iac-exporter

Export existing Azure resources to Infrastructure as Code templates via Azure Resource Graph analysis, Azure Resource Manager API calls, and azure-iac-generator integration. Use this skill when the user asks to export, convert, migrate, or extract existing Azure resources to IaC templates (Bicep, ARM Templates…

github/awesome-copilot · 70 tokens

Senior Cloud Architect

Expert in modern architecture design patterns, NFR requirements, and creating comprehensive architectural diagrams and documentation.

github/awesome-copilot · 22 tokens

SE: Architect

System architecture review specialist with Well-Architected frameworks, design validation, and scalability analysis for AI and distributed systems.

github/awesome-copilot · 26 tokens

FAI Kubernetes Expert

Kubernetes specialist — pod scheduling, GPU resource management, network policies, Helm charts, GitOps with Flux/ArgoCD, and production-grade AI workload orchestration on AKS.

frootai/frootai · 42 tokens

vllm-deployer

An agent definition for deploying vLLM, a tool for serving large language models. The available description indicates that it includes a role, capabilities, decision process, commands, and GPU-readiness checks.

aws-samples/sample-oh-my-aidlcops · 89 tokens