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 manu14357/zskills --skill azure-rbacgit clone --depth 1 https://github.com/manu14357/zskillsWrote 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/manu14357/zskills/azure-rbac)<a href="https://agentmods.dev/skills/manu14357/zskills/azure-rbac"><img src="https://agentmods.dev/badge/skills/manu14357/zskills/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/manu14357/zskills/azure-rbac"><img src="https://agentmods.dev/badge/skills/manu14357/zskills/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 | $0.00062 | $0.02498 |
| Opus 5 | $0.00031 | $0.01249 |
| Sonnet 5 | $0.00012 | $0.00500 |
| Haiku 4.5 | $0.00006 | $0.00250 |
Grade A, and why
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 11d 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 — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Azure RBAC
Grant the minimum required access at management group, subscription, resource group, or resource scope. Build scalable, auditable identity infrastructure using groups, managed identities, and Privileged Identity Management.
Use This Skill When
- The user needs role assignment design or access error diagnosis
- The user wants to secure team access or workload permissions
- The user needs compliance-ready access governance (audit trail, reviews)
- The user wants to migrate from per-user to group-based RBAC
Context: RBAC Maturity
Immature: Ad hoc assignments, direct user permissions, no audit trail
Developing: Some group-based access, manual reviews, audit logs exist
Managed: Group-based RBAC, scoped assignments, automated access reviews, PIM for elevation → Target
Optimized: Zero Trust with managed identities, ephemeral access, real-time risk-based access decisions
Required Inputs
- Principals: Users, groups, service principals, managed identities
- Required actions: Specific operations (create, delete, read, write)
- Resource scope: Subscription, resource group, or individual resource
- Compliance needs: Audit trail required? Access reviews? Time-bound access?
- Escalation model: Who approves elevated access? How long is it valid?
Decision Tree
Is this human access (person) or workload identity (application)?
├─ Human:
│ ├─ Is this just viewing resources? → Reader role
│ ├─ Is this deploying/configuring? → Contributor role (at resource group scope)
│ ├─ Is this infrastructure admin work? → PIM-eligible Owner (with approval)
│ └─ Is this on a single resource? → Role-scoped to that resource
└─ Workload:
├─ Is this a new app? → Create user-assigned managed identity, assign narrow role
├─ Needs secret access? → Key Vault Secrets User role
├─ Needs storage access? → Storage Blob Data Contributor (scoped)
└─ Needs database? → SQL DB Contributor (scoped)
Should this access be permanent or temporary?
├─ Permanent → Standard role assignment (group-based for humans)
└─ Temporary/Elevated → PIM-eligible role (approval workflow, 4-hour max)
How many users need this access?
├─ 1-2 people → Consider if per-user assignment is necessary
├─ 3+ people → MUST use security group assignment
└─ 10+ people → Automate group membership from identity provider
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.
- 11d ago First seen · 292 lines · 62 tokens per session scan A ece67fda4eee
azure-rbac is a skill published in the GitHub repository manu14357/zskills (16 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 2,498 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…