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 skills add jonathan-vella/apex-accelerator --skill apex-azure-rbacgit clone --depth 1 https://github.com/jonathan-vella/apex-acceleratorWrote 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.
[](https://agentmods.dev/skills/jonathan-vella/apex-accelerator/apex-azure-rbac)<a href="https://agentmods.dev/skills/jonathan-vella/apex-accelerator/apex-azure-rbac"><img src="https://agentmods.dev/badge/skills/jonathan-vella/apex-accelerator/apex-azure-rbac/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.
<a href="https://agentmods.dev/skills/jonathan-vella/apex-accelerator/apex-azure-rbac"><img src="https://agentmods.dev/badge/skills/jonathan-vella/apex-accelerator/apex-azure-rbac.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00107 | $0.01664 |
| Opus 5.5 | $0.00043 | $0.00666 |
| Sonnet 5.5 | $0.00021 | $0.00333 |
| Haiku 4.5 | $0.00011 | $0.00166 |
Grade A, and why
apex-azure-rbac 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 7d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Azure RBAC Skill
Find the minimal built-in Azure role that grants the requested permissions to
an identity, then generate the az role assignment create CLI and a Bicep
Microsoft.Authorization/roleAssignments snippet. Custom roles only when no
built-in fits.
Rules
- Least privilege first — prefer the most narrowly-scoped built-in role that satisfies the permissions; only define a custom role when no built-in fits
- Role assignment scope matters — prefer resource-level or resource-group scope over subscription scope
- Discover roles via
mcp_azure-mcp_documentation— invoke withcommand: "microsoft_docs_search"to query for built-in role definitions before generating any CLI or Bicep - Verify with
az role definition list— cross-check the discovered role against the live Azure RBAC catalogue - Use
guid()in Bicep forMicrosoft.Authorization/roleAssignmentsnames so assignments are idempotent across re-deploys; setprincipalType: 'ServicePrincipal'for managed identities - Granting roles requires elevated permission — see Prerequisites for Granting Roles below
- Generate before executing — require explicit approval for the exact principal, role and scope; generic role guidance does not confer write permission for role creation or assignment
- Authentication is separate — use canonical auth guidance; Azure RBAC does not grant Microsoft Graph API consent
- Out of scope: deploying resources (use
apex-azure-deploy), security audits (useapex-azure-compliance)
Steps
- Identify the operation — what action does the identity need (read storage, manage keys, deploy resources, etc.)?
- Search Microsoft docs — invoke
mcp_azure-mcp_documentationwithcommand: "microsoft_docs_search"and a query such as"Azure built-in role <operation>"(e.g.,"Azure built-in role read blob storage"); collect candidate role names + role IDs - Verify against the live catalogue — preserve every permission block and scope:
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.
- 7d ago Changed 8d011041e92b
- 22d ago Changed · +25 lines ff390882ae2f
- 23d ago First seen · 128 lines · 107 tokens per session scan A c71f87706029
apex-azure-rbac is a skill published in the GitHub repository jonathan-vella/apex-accelerator (50 stars, last pushed yesterday), licensed MIT. It adds 107 tokens to every session and 1,664 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-23.
Other skills, from other repositories
chaos-experiment
Design and document chaos engineering experiments. Guide steady state baseline, hypothesis formation, failure injection plans, and results analysis. Use when you say "design a chaos experiment", "plan a game day", "failure injection", "test resilience", or "chaos engineering". Do NOT use for security threat analysis…
infrastructure-as-code
Domain: DevOps & Cloud Engineering.
cloud-solution-architect
Design well-architected Azure cloud systems — 10 design principles, 6 architecture styles, 44 design patterns, technology choices, WAF pillars.
bicep-avm-mastery
Azure Verified Modules (AVM), Bicep best practices, and MCP-powered infrastructure as code for Azure.
foundry-agent-platform
Microsoft Foundry agent deployment, orchestration, and cloud-native AI service patterns.
sse-streaming
POST-based Server-Sent Events streaming for Azure Functions — HTTP streaming, chunked response parsing, reconnection.