unified-secops-platform

unified-secops-platform is a skill for Claude Code, Codex from vinayaklatthe/microsoft-security-skills. It costs 154 tokens per session (1,751 once invoked), scanned A, original, MIT.

Guidance for using Microsoft's unified security operations platform, which brings Sentinel, Defender XDR, Security Copilot, threat intelligence, and exposure management into the Defender portal.

In plain words
What is it for?
Use it to onboard Sentinel to the Defender portal, unify SIEM and XDR incidents, and coordinate investigations across Microsoft security products.
Why use it?
It helps security teams work from one incident queue and portal instead of switching between separate tools and manually correlating alerts.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to onboard Sentinel to the Defender portal, unify SIEM and XDR incidents, and coordinate investigations across Microsoft security products.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vinayaklatthe/microsoft-security-skills/unified-secops-platform
Install

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.

Any agent
npx skills add vinayaklatthe/microsoft-security-skills --skill unified-secops-platform
Clone the repo
git clone --depth 1 https://github.com/vinayaklatthe/microsoft-security-skills

Made for: Claude Code, Codex.

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 unified-secops-platform

README.md
[![agentmods](https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/unified-secops-platform/github.svg)](https://agentmods.dev/skills/vinayaklatthe/microsoft-security-skills/unified-secops-platform)
Your own site
<a href="https://agentmods.dev/skills/vinayaklatthe/microsoft-security-skills/unified-secops-platform"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/unified-secops-platform/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 unified-secops-platform

Your own site · 80×15
<a href="https://agentmods.dev/skills/vinayaklatthe/microsoft-security-skills/unified-secops-platform"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/unified-secops-platform.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 154 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,751 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 $0.00154 $0.01751
Opus 5 $0.00077 $0.00875
Sonnet 5 $0.00031 $0.00350
Haiku 4.5 $0.00015 $0.00175

Measured 9d ago against content hash 30348df90cc2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

unified-secops-platform 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.

skills/unified-secops-platform/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Unified SecOps Platform (Microsoft Defender portal)

The unified security operations platform consolidates SIEM (Microsoft Sentinel), XDR (Microsoft Defender XDR), Microsoft Security Copilot, Microsoft Defender Threat Intelligence, and Microsoft Security Exposure Management into a single experience in the Microsoft Defender portal (security.microsoft.com).

When to use

Standardising the SOC on one portal, unifying the incident queue across SIEM and XDR signals, and reducing context-switching for analysts.

Do not use this skill for:

  • Workspace, data connector, or analytics rule design only (use sentinel)
  • Endpoint/identity/email/cloud-app investigation only (use defender-xdr)
  • Threat-hunting query writing only (use sentinel for KQL guidance)

Pick the right starting question

Today's pain Use the unified portal to... Notes
Analysts toggle between Azure portal and security.microsoft.com Onboard Sentinel to the Defender portal One queue, one entity graph
Two incident queues, manual correlation Unified incident queue across SIEM + XDR Auto-correlation, single triage
Hunting across Defender + Sentinel tables is two queries Advanced hunting in the Defender portal Single KQL surface
Need attack-surface and attack-path view Add Exposure Management Prioritise by blast radius
SOC wants AI assist inline Add Security Copilot embedded Per-incident summary

Rule of thumb: if your SOC has Sentinel and Defender XDR, you should be in the unified portal. The Azure Sentinel portal is the legacy surface; new investments land in the Defender portal first.

Approach

  1. Confirm prerequisites - A Microsoft Sentinel workspace, Microsoft Defender XDR onboarded with at least one Defender product, the required Entra and Sentinel RBAC roles for the onboarding admin, and tenant alignment between the Sentinel workspace and the Defender XDR tenant. Verify: the workspace and Defender XDR are in the same tenant; the admin holds Microsoft Sentinel Contributor + a Defender XDR security role.
  2. Pick the primary workspace - Only one Sentinel workspace can be the primary in the unified portal per tenant. If you run multiple workspaces, decide which carries the unified experience and which remain Azure-portal-only. Plan migrations accordingly. Verify: workspace inventory documents which is primary and the rationale.
  3. Onboard Sentinel to the Defender portal - From the Defender portal, connect the Log Analytics workspace. Onboarding is non-destructive to existing Sentinel content (analytics rules, hunting queries, playbooks) but changes where analysts work. Verify: Defender portal → Investigation & response shows incidents from both Sentinel analytics rules and Defender XDR detections.
  4. Validate the unified incident queue - Incidents and alerts from Sentinel and Defender XDR merge into one queue with shared entities, enabling single-pane triage. Confirm Sentinel incidents that previously stood alone now correlate to XDR alerts where appropriate. Verify: an end-to-end test attack (e.g. simulated phishing + sign-in anomaly) creates one correlated incident, not two.
  5. Use unified advanced hunting - Query both Sentinel and XDR tables together with KQL in the Defender portal hunting experience. Retire duplicate hunting queries that only existed to bridge the two surfaces. Verify: a hunting query joining a Defender table (e.g. DeviceLogonEvents) and a Sentinel table runs in one window.
  6. Layer in cross-cutting capabilities - Add Security Copilot for inline AI assistance, Threat Intelligence for IOC management, and Exposure Management for attack-surface and attack-path insight. Each adds value but each adds licence/SCU cost - sequence by SOC pain. Verify: each capability has a named SOC use case before enabling, not just a toggle flip.
  7. Validate RBAC end-to-end - Defender portal unified RBAC governs access to the merged experiences. Map existing Sentinel and Defender role assignments to the unified model and confirm no role escalation or unintended access has appeared. Verify: a least-privilege analyst sees only their assigned workloads in both incident queue and hunting.
  8. Migrate analyst workflow - Update runbooks, shift links, and training to point at the Defender portal. Treat the Azure Sentinel portal as legacy for analyst day-to-day.

Read the full file on GitHub · 121 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 · 121 lines · 154 tokens per session scan A 30348df90cc2

Subscribe to this mod's changes

unified-secops-platform is a skill published in the GitHub repository vinayaklatthe/microsoft-security-skills (173 stars, last pushed 2mo ago), licensed MIT. It adds 154 tokens to every session and 1,751 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 2026-09-03.

Related

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…

ericrisco/rsc-harness · 82 tokens

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…

microsoft/vscode · 72 tokens

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.

microsoft/vscode · 36 tokens

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.

nexu-io/open-design · 53 tokens

skill-writing-plans

Create zero-context implementation plans with bite-sized tasks — use for multi-step feature planning.

nyldn/claude-octopus · 21 tokens

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.

microsoft/Agents · 56 tokens