Azure DevOps Skills is a collection of reusable instruction bundles that teach AI coding assistants how to perform recurring Azure DevOps tasks. The examples support workflows such as reviewing backlogs, listing active work, and managing iterations through the Azure DevOps MCP server.
Borrowing it
Nothing to install: this file belongs to microsoft/azure-devops-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/microsoft/azure-devops-skills/main/.github/skills/security-alert-review/SKILL.mdgit clone --depth 1 https://github.com/microsoft/azure-devops-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/microsoft/azure-devops-skills/security-alert-review)<a href="https://agentmods.dev/skills/microsoft/azure-devops-skills/security-alert-review"><img src="https://agentmods.dev/badge/skills/microsoft/azure-devops-skills/security-alert-review.svg" alt="Measured on agentmods" 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 | $0.00039 | $0.01347 |
| Opus 5 | $0.00019 | $0.00674 |
| Sonnet 5 | $0.00008 | $0.00269 |
| Haiku 4.5 | $0.00004 | $0.00135 |
Grade A, and why
security-alert-review 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 8d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security alert review
This skill works in the context of a project and a repository. Both are required to retrieve alerts.
Project selection
- If the user provides a project name in their request (for example, "for Contoso"), use that project directly and do not call
core_list_projects. - If the user does not provide a project name, first ask the user once to provide the project name.
- If the project name is still not provided after asking once, call
core_list_projectsto return a list of projects the user can choose from.
Repository selection
- If the user provides a repository name, use that repository directly.
- If the user does not specify a repository, ask the user once for the repository name.
- If the repository name is still not provided after asking once, call
repo_list_repos_by_projectto list available repositories for the user to choose from.
Tools
Use Azure DevOps MCP Server tools for all interactions with Azure DevOps.
core_list_projects: Get a list of projects in the organization.repo_list_repos_by_project: Get a list of repositories for a project.advsec_get_alerts: Get Advanced Security alerts for a repository, with optional filters for severity, state, alert type, and confidence level.advsec_get_alert_details: Get detailed information about a specific alert by ID.
Rules
1. List alerts for a repository
- When the user asks to list alerts, show security alerts, or review alerts, call
advsec_get_alertsfor the specified project and repository. - Apply filters based on the user's request:
- Severity: filter by
severities(for example, "show critical alerts" →["Critical"]). - State: filter by
states(for example, "show active alerts" →["Active"]). - Alert type: filter by
alertType(for example, "show dependency alerts" →"Dependency"). Valid types are:Dependency,Secret,Code.
- Severity: filter by
- Always include
confidenceLevels: ["High", "Other"]on every call toadvsec_get_alertsunless the user explicitly requests a specific confidence filter. - If the user does not specify filters, show all active alerts on the default branch by default (use
onlyDefaultBranch: true,states: ["Active"], andconfidenceLevels: ["High", "Other"]). - Show the results in a table.
- If there are no alerts, explicitly state that there are no alerts matching the criteria for this repository.
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.
- 8d ago First seen · 106 lines · 39 tokens per session scan A d075d251ade6
security-alert-review is a skill published in the GitHub repository microsoft/azure-devops-skills (44 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 1,347 once invoked, about $0.0002 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…
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…
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…