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 julianobarbosa/claude-code-skills --skill azure-devopsgit clone --depth 1 https://github.com/julianobarbosa/claude-code-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/julianobarbosa/claude-code-skills/azure-devops)<a href="https://agentmods.dev/skills/julianobarbosa/claude-code-skills/azure-devops"><img src="https://agentmods.dev/badge/skills/julianobarbosa/claude-code-skills/azure-devops.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 41 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00036 | $0.04830 |
| Opus 5 | $0.00018 | $0.02415 |
| Sonnet 5 | $0.00007 | $0.00966 |
| Haiku 4.5 | $0.00004 | $0.00483 |
Grade A, and why
azure-devops scanned grade A with 1 finding 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 7d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -H "Authorization: Basic ${AUTH}" https://dev.azure.com/{org}/_apis/projects How it starts
The opening of the file, as written. The whole thing — 618 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Azure DevOps REST API Skill
Comprehensive guide for Azure DevOps REST API v7.2 operations including work items, pipelines, repositories, test plans, wikis, and search functionality.
Quick Reference
| Area | Base URL | MCP Tool Prefix |
|---|---|---|
| Core | dev.azure.com/{org}/_apis/ |
mcp__ado__core_* |
| Work Items | dev.azure.com/{org}/{project}/_apis/wit/ |
mcp__ado__wit_* |
| Pipelines | dev.azure.com/{org}/{project}/_apis/pipelines/ |
mcp__ado__pipelines_* |
| Git/Repos | dev.azure.com/{org}/{project}/_apis/git/ |
mcp__ado__repo_* |
| Test Plans | dev.azure.com/{org}/{project}/_apis/testplan/ |
mcp__ado__testplan_* |
| Wiki | dev.azure.com/{org}/{project}/_apis/wiki/ |
mcp__ado__wiki_* |
| Search | almsearch.dev.azure.com/{org}/_apis/search/ |
mcp__ado__search_* |
Authentication Methods
Personal Access Token (PAT)
# Base64 encode empty username with PAT
AUTH=$(echo -n ":${PAT}" | base64)
curl -H "Authorization: Basic ${AUTH}" https://dev.azure.com/{org}/_apis/projects
OAuth 2.0 Scopes
| Scope | Access Level |
|---|---|
vso.work |
Read work items |
vso.work_write |
Create/update work items |
vso.code |
Read source code |
vso.code_write |
Create branches, PRs |
vso.build_execute |
Run pipelines |
vso.test |
Read test plans |
vso.wiki |
Read wikis |
API Versioning
Format: {major}.{minor}[-{stage}[.{resource-version}]]
- Current:
7.2-preview.3 - Example:
api-version=7.2-preview.3
1. Work Item Operations
Available MCP Tools
mcp__ado__wit_get_work_item - Get single work item
mcp__ado__wit_get_work_items_batch_by_ids - Get multiple work items
mcp__ado__wit_my_work_items - Get items assigned to me
mcp__ado__wit_create_work_item - Create new work item
mcp__ado__wit_update_work_item - Update work item fields
mcp__ado__wit_update_work_items_batch - Bulk update work items
mcp__ado__wit_add_work_item_comment - Add comment to work item
mcp__ado__wit_list_work_item_comments - List work item comments
mcp__ado__wit_add_child_work_items - Create child work items
mcp__ado__wit_work_items_link - Link work items together
mcp__ado__wit_work_item_unlink - Remove work item links
mcp__ado__wit_link_work_item_to_pull_request - Link to PR
mcp__ado__wit_add_artifact_link - Add artifact links (branch, commit, build)
mcp__ado__wit_get_work_item_type - Get work item type definition
mcp__ado__wit_list_backlogs - List team backlogs
mcp__ado__wit_list_backlog_work_items - Get backlog items
mcp__ado__wit_get_work_items_for_iteration - Get sprint items
mcp__ado__wit_get_query - Get saved query
mcp__ado__wit_get_query_results_by_id - Execute saved query
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/git-repos-reference.md 9.2 KB
- references/pipelines-reference.md 10 KB
- references/test-plans-reference.md 10.0 KB
- references/wiki-search-reference.md 10 KB
- references/work-items-reference.md 12 KB
- scripts/ado-cli.sh 12 KB runs code
- scripts/pipelines.py 11 KB runs code
- scripts/pull-requests.py 15 KB runs code
- scripts/work-items.py 10 KB runs code
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.
- 7d ago First seen · 618 lines · 36 tokens per session scan A d422141fc460
azure-devops is a skill published in the GitHub repository julianobarbosa/claude-code-skills (10 stars, last pushed 12d ago), licensed MIT. It adds 36 tokens to every session and 4,830 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
mem0-test-integration
Verify a Mem0 integration produced by /mem0-integrate. Runs in the same workspace on the same branch (loose coupling) — installs dependencies, runs the repo's native test suite, then exercises a real end-to-end smoke flow against the user's API key. Produces a scorecard. TRIGGER when: user has just run /mem0-integrate…
voiden
Create and edit Voiden .void files for API testing. Covers the .void file format and all enabled extension block types.
API Test Suite Generator
Automatically generate comprehensive API test suites from OpenAPI specifications covering CRUD operations, error handling, authentication, pagination, and edge cases.
bruno
Comprehensive operational skill specification for Anthropic Claude to automate, script, troubleshoot, and optimize Bruno API Client, Bru markup language (.bru), CLI runner (@usebruno/cli), and CI/CD test pipelines.
task-land
Land a work item's pull request with Baron — take it out of draft and merge it. Use when the user says merge it / land it / birleştir / it's approved, ship this PR. Do NOT shell out to gh or az for this; Baron owns the provider call, including the parts that have no REST route.
fastapi-docs
FastAPI 0.115+ — path/query params, Pydantic, dependency injection, OAuth2/JWT, middleware, WebSocket, testing.