What is defender-xdr?

Microsoft Defender XDR is a security suite that combines alerts from devices, user accounts, email, collaboration tools, and cloud apps. It groups related signals into incidents with timelines, evidence, and attack-graph context.

Use it to onboard Microsoft security workloads, investigate incidents, run advanced searches with KQL, and create or tune detections across the Microsoft 365 environment.

It reduces the need to investigate each Microsoft security product separately. Correlating the signals can show the broader attack story and support coordinated response actions.

defender-xdr — Skill for Claude Code and Codex by vinayaklatthe

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 defender-xdr

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/defender-xdr/github.svg)](https://agentmods.dev/skills/vinayaklatthe/microsoft-security-skills/defender-xdr)

Your own site

<a href="https://agentmods.dev/skills/vinayaklatthe/microsoft-security-skills/defender-xdr"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/defender-xdr/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/vinayaklatthe/microsoft-security-skills/defender-xdr"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/defender-xdr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 196 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,983 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.

Model	Per session	Once invoked
Fable 5.1	$0.00196	$0.01983
Opus 5	$0.00098	$0.00992
Sonnet 5	$0.00039	$0.00397
Haiku 4.5	$0.00020	$0.00198

Measured 11d ago against content hash 77d11f372074, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

defender-xdr 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.

skills/defender-xdr/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Microsoft Defender XDR

Microsoft Defender XDR is a unified pre- and post-breach defence suite. It natively correlates signals across endpoints (MDE), identities (MDI + Entra ID Protection), email/collaboration (MDO), and cloud apps (MDA) to deliver a single prioritised incident with the full attack story - graph, timeline, evidence, and recommended actions.

When to use

Running coordinated detection and response across the Microsoft 365 estate from one portal (security.microsoft.com), instead of investigating each workload in isolation. Also when you need the attack disruption feature - it requires the XDR correlation.

Do not use this skill when ingesting third-party logs or writing custom KQL detections across non-Microsoft sources (sentinel), merging Sentinel + Defender into one portal (unified-secops-platform), or tuning endpoint-only policies (defender-for-endpoint).

Map the signal to the source workload

XDR is only as good as the workloads feeding it. Use this to confirm what's onboarded and which alerts are missing.

If the signal is...	Source workload	Required licence
Process tree, network connection, file hash on a device	Defender for Endpoint (MDE) P2	M365 E5 / MDE P2
Kerberos anomaly, DCSync, AD CS abuse, on-prem lateral movement	Defender for Identity (MDI)	M365 E5 / EMS E5
Risky sign-in, leaked credentials, anomalous token use	Entra ID Protection	Entra ID P2
Phishing URL click, malicious attachment detonation, BEC	Defender for Office 365 P2	M365 E5 / MDO P2
Risky OAuth app, anomalous SaaS upload, MCAS-style alert	Defender for Cloud Apps (MDA)	MDA standalone or E5
Azure resource alert, AKS pod compromise	Defender for Cloud	DfC plan-based

Rule of thumb: if an incident shows "1 alert, 1 entity," a workload is missing. A real attack always touches at least two of the above.

Approach

Onboard the core workloads first — In order: MDE (highest endpoint signal), MDI (lateral movement), Entra ID Protection, MDO. Add MDA when SaaS apps are in scope. Each workload onboarded to its own portal still surfaces in the unified Defender portal. Verify: Incidents view shows alerts from at least 3 different ServiceSource values after 24 hours.

Read the full file on GitHub · 128 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.

11d ago First seen · 128 lines · 196 tokens per session scan A 77d11f372074

Subscribe to this mod's changes

defender-xdr is a skill published in the GitHub repository vinayaklatthe/microsoft-security-skills (173 stars, last pushed 2mo ago), licensed MIT. It adds 196 tokens to every session and 1,983 once invoked, about $0.0010 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.

Security ai-agents copilot defender entra entra-id microsoft

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

defender-xdr