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 sentinelgit 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/sentinel)<a href="https://agentmods.dev/skills/vinayaklatthe/microsoft-security-skills/sentinel"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/sentinel/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/sentinel"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/sentinel.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 | $0.00203 | $0.02038 |
| Opus 5 | $0.00102 | $0.01019 |
| Sonnet 5 | $0.00041 | $0.00408 |
| Haiku 4.5 | $0.00020 | $0.00204 |
Grade A, and why
sentinel 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.
How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Microsoft Sentinel
Microsoft Sentinel is a cloud-native SIEM + SOAR built on a Log Analytics workspace and delivered through the Microsoft Defender portal as part of the unified SecOps platform. It ingests logs from Microsoft and third-party sources, runs scheduled and near-real-time detections in KQL, correlates alerts into incidents, and orchestrates response via Logic Apps playbooks.
When to use
Centralising security logs from Microsoft and third-party sources, building detections, hunting across data, and automating response. Use Sentinel when you need a single SIEM across clouds, on-prem, and SaaS - not only Microsoft 365.
Do not use this skill when the goal is only correlating M365 alerts (use defender-xdr)
or onboarding the existing Sentinel workspace into the unified Defender portal (use
unified-secops-platform).
Route the log source to the right ingestion tier
Pick the tier first, then the connector. Tier choice drives cost more than anything else.
| If the log is... | Send to | Retention default | Cost shape |
|---|---|---|---|
| High-fidelity security log used in detections (sign-ins, audit, EDR) | Analytics | 90 days free, then paid | Pay per GB (commitment tier) |
| Verbose but query-occasionally (CDN, custom app, firewall info) | Basic logs | 30 days, no analytics rules | ~1/5th of Analytics |
| High-volume, low-fidelity, search-only (NetFlow, DNS, proxy) | Auxiliary logs | 30 days hot + 12 mo long-term | ~1/8th of Analytics |
| Long-term archive for compliance / rare investigation | Azure Data Explorer (ADX) | Years | ADX cluster cost |
| Microsoft 365 / Defender XDR alerts only | Free via M365 Defender connector | N/A | Free |
Rule of thumb (2026 pricing): if a table averages > 50 GB/day and analytics rules don't query it, it does not belong in the Analytics tier. Moving DNS or proxy logs to Auxiliary typically cuts Sentinel bills by 30-50%.
Approach
- Estimate volume and pick commitment tier — Run the Sentinel pricing calculator with a
30-day sample (use
Usage | summarize sum(Quantity) by bin(TimeGenerated, 1d), DataType). Commitment tiers start at 100 GB/day and drop the per-GB rate ~50% vs Pay-As-You-Go. Verify: daily ingestion stable within ±20% of estimate before committing.
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.
- 9d ago First seen · 129 lines · 203 tokens per session scan A 3e62685575bf
sentinel is a skill published in the GitHub repository vinayaklatthe/microsoft-security-skills (173 stars, last pushed 2mo ago), licensed MIT. It adds 203 tokens to every session and 2,038 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 2026-09-03.
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.