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 vinayaklatthe/microsoft-security-skills --skill paw-designgit clone --depth 1 https://github.com/vinayaklatthe/microsoft-security-skillsWrote 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/vinayaklatthe/microsoft-security-skills/paw-design)<a href="https://agentmods.dev/skills/vinayaklatthe/microsoft-security-skills/paw-design"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/paw-design/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/vinayaklatthe/microsoft-security-skills/paw-design"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/paw-design.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 | $0.00155 | $0.01808 |
| Opus 5 | $0.00077 | $0.00904 |
| Sonnet 5 | $0.00031 | $0.00362 |
| Haiku 4.5 | $0.00015 | $0.00181 |
Grade A, and why
paw-design 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 12d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Privileged Access Workstation (PAW) Design
A Privileged Access Workstation (PAW) is a hardened, dedicated device used only for privileged tasks - isolating sensitive accounts from browsing, email, and arbitrary apps. PAWs are the device pillar of Microsoft's privileged access strategy and the enforcement point for the clean source principle.
When to use
Protecting administrators of high-value systems (Entra control plane, Azure root, domain controllers, identity infrastructure - "Tier 0") from credential theft, browser exploit, and supply-chain attack. Use this skill to choose the device tier, harden the build, and enforce PAW-only access via CA.
Do not use this skill for general endpoint hardening (defender-for-endpoint) or
device compliance baseline (intune-device-mgmt).
Pick the device profile by admin tier
The enterprise access model maps admin roles to three device profiles. Wrong tier = either over-spending or under-protecting.
| Tier | Roles in scope | Device profile | What's allowed |
|---|---|---|---|
| Privileged (PAW) | Global Admin, Privileged Auth Admin, Tier 0 Azure Owner, Domain Admin, DC operators | Dedicated hardened device | Admin portals only; no email, no browsing |
| Specialized | Workload admins (Exchange, SharePoint, Intune, SQL DBA), Tier 1 Azure Contributor | Hardened build; some productivity | Admin portals + curated productivity (Office) |
| Enterprise | Help desk, Tier 2 ops, Reports Reader, Security Reader | Standard managed device + strong baseline | Full productivity with MDE + ASR + tamper protection |
Rule of thumb: the test for "needs a PAW" is can this account log into a domain controller, modify Conditional Access, or assume the root Azure subscription? If yes, PAW. If only managing one workload, Specialized. The PAW population should be small (typically < 1% of admins).
Approach
- Adopt the enterprise access model — Map every privileged role to control / management / data plane. Tier 0 = control plane (identity, cloud control plane, on-prem AD). Tier 1 = workload admins. Tier 2 = ops / read-only. Devices, accounts, and access paths must match the tier. Verify: tier mapping document signed off; Tier 0 role count documented.
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.
- 12d ago First seen · 119 lines · 155 tokens per session scan A 2375294cc67a
paw-design is a skill published in the GitHub repository vinayaklatthe/microsoft-security-skills (173 stars, last pushed 2mo ago), licensed MIT. It adds 155 tokens to every session and 1,808 once invoked, about $0.0008 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
power-automate
Use when operating Microsoft Power Automate cloud flows from code — create, enable, update, list or delete via the Dataverse Web API (workflow table, category 5) with Entra ID OAuth2, plus run-history debugging. NOT designing the flow definition (that is automation-flows), NOT picking a platform by billing model (that…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
generate-run-commands
Generate or modify run commands for the current session. Use when the user wants to set up or update run commands that appear in the session's Run button.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
skill-writing-plans
Create zero-context implementation plans with bite-sized tasks — use for multi-step feature planning.
bf-to-agents-sdk-dotnet-migration
Use when migrating a Bot Framework .NET SDK bot to Microsoft 365 Agents SDK. Triggered by projects that depend on packages: Microsoft.Bot.Builder or Microsoft.Bot.Builder.Integration.AspNet.Core that want to migrate to Agents SDK.