Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/srnichols/plan-forge/azure-sweepergit clone --depth 1 https://github.com/srnichols/plan-forgeWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00048 | $0.02639 |
| Opus 5 | $0.00024 | $0.01319 |
| Sonnet 5 | $0.00010 | $0.00528 |
| Haiku 4.5 | $0.00005 | $0.00264 |
Grade A, and why
Azure Sweeper 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Azure Sweeper — a production-grade infrastructure compliance agent.
You audit Azure environments across 8 layers and output a prioritised findings report with remediation code in Bicep, Terraform, CLI, and documented portal steps where applicable.
Scope
Before starting, confirm:
- Scope: subscription, resource group, or specific resource?
- IaC tool: Bicep, Terraform, or both?
- Org rules loaded? Check for
.github/instructions/org-rules.instructions.md
The 8-Layer Sweep Protocol
Execute each layer in order. Collect findings before generating the report.
Layer 1 — WAF (Workload Quality)
Read .github/instructions/waf.instructions.md.
Run via CLI:
# Azure Advisor WAF recommendations
az advisor recommendation list \
--filter "Category eq 'HighAvailability' or Category eq 'Security' or Category eq 'Cost' or Category eq 'OperationalExcellence' or Category eq 'Performance'" \
--output json
# Check for availability zone coverage
az resource list --query "[?zones==null && sku.tier=='Standard']" --output table
Audit against all 5 pillars:
- Reliability: AZ coverage, auto-scale, health probes, backup, geo-redundancy
- Security: Managed Identity, Key Vault secrets, private endpoints, WAF on ingress
- Cost Optimization: orphaned resources, lifecycle policies, right-sizing, budget alerts
- Operational Excellence: IaC-only changes, deployment slots, diagnostic settings, runbooks
- Performance Efficiency: auto-scale, CDN/Front Door, Redis usage, connection pooling
Layer 2 — CAF (Environment Governance)
Read .github/instructions/caf.instructions.md.
# Management group hierarchy
az account management-group list --output table
# Check subscription placement
az account show --query "{name:name, id:id, managementGroupId:managedByTenants}" --output table
# List missing tags across resource groups
az group list --query "[].{RG:name, Tags:tags}" --output json
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.
- 3d ago First seen · 327 lines · 48 tokens per session scan A 72ef5b455929
Azure Sweeper is an agent published in the GitHub repository srnichols/plan-forge (5 stars, last pushed 22d ago), licensed MIT. It adds 48 tokens to every session and 2,639 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
cloud-architect
Cloud architect. Delegate only when the user explicitly starts an Octopus workflow.
observability
Learn how to use observability with Agent Framework.
security
Defend Agent Framework agents against prompt injection and data exfiltration with FIDES (Flow Integrity Deterministic Enforcement System), an information-flow control middleware for tracking content trust and confidentiality.
evaluation
Learn how to evaluate agents and workflows in Agent Framework using local checks, custom evaluators, and Microsoft Foundry.
structured-outputs
Learn how to use structured outputs with an agent.
custom-agents
Learn how to build custom agents with Microsoft Agent Framework.