wiql-queries

wiql-queries is a skill for Claude Code from JoshuaRamirez/ms-ado-az-claude-code-plugin. It costs 93 tokens per session (1,766 once invoked), scanned A, original, MIT.

A skill for writing and running WIQL, the query language used to find and filter Azure DevOps work items.

In plain words
What is it for?
Use it to find bugs, tasks, assigned items, sprint items, or work items matching specific states and fields.
Why use it?
It helps form valid searches while accounting for limits and syntax differences from SQL.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the ado-work-items plugin — 5 skills, 2 commands, 1 agent shipped together

Good fit Use it to find bugs, tasks, assigned items, sprint items, or work items matching specific states and fields.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/joshuaramirez/ms-ado-az-claude-code-plugin/wiql-queries
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 JoshuaRamirez/ms-ado-az-claude-code-plugin --skill wiql-queries
Clone the repo
git clone --depth 1 https://github.com/JoshuaRamirez/ms-ado-az-claude-code-plugin

Made for: Claude Code.

Or install ado-work-items, the plugin that ships this one along with the rest of its 5 skills, 2 commands, 1 agent.

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 wiql-queries

README.md
[![agentmods](https://agentmods.dev/badge/skills/joshuaramirez/ms-ado-az-claude-code-plugin/wiql-queries/github.svg)](https://agentmods.dev/skills/joshuaramirez/ms-ado-az-claude-code-plugin/wiql-queries)
Your own site
<a href="https://agentmods.dev/skills/joshuaramirez/ms-ado-az-claude-code-plugin/wiql-queries"><img src="https://agentmods.dev/badge/skills/joshuaramirez/ms-ado-az-claude-code-plugin/wiql-queries/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 wiql-queries

Your own site · 80×15
<a href="https://agentmods.dev/skills/joshuaramirez/ms-ado-az-claude-code-plugin/wiql-queries"><img src="https://agentmods.dev/badge/skills/joshuaramirez/ms-ado-az-claude-code-plugin/wiql-queries.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,766 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 $0.00093 $0.01766
Opus 5 $0.00046 $0.00883
Sonnet 5 $0.00019 $0.00353
Haiku 4.5 $0.00009 $0.00177

Measured 10d ago against content hash 6611e9f8c6b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

wiql-queries 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 10d 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/wiql-queries/SKILL.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

WIQL Query Reference (Verified)

CRITICAL LIMITATIONS - READ FIRST

  1. NO TOP CLAUSE - WIQL does NOT support SELECT TOP N like SQL Server. Limit results with shell:

    az boards query --wiql "..." -o table | head -10
    
  2. Use explicit project name - The @project macro is unreliable in CLI:

    -- UNRELIABLE:
    WHERE [System.TeamProject] = @project
    
    -- RELIABLE:
    WHERE [System.TeamProject] = 'YourProjectName'
    
  3. Only flat queries supported - The CLI only supports flat queries, not tree/hierarchical queries.

  4. NO LIKE OPERATOR - WIQL does NOT support SQL-style LIKE patterns. Use CONTAINS instead:

    -- DOES NOT WORK:
    WHERE [System.Title] LIKE '%keyword%'
    
    -- USE THIS INSTEAD:
    WHERE [System.Title] CONTAINS 'keyword'
    
  5. CANNOT ORDER BY System.Parent - Sorting by parent ID is not supported:

    -- DOES NOT WORK:
    ORDER BY [System.Parent]
    
    -- WORKAROUND: Filter by parent IDs with IN clause, sort client-side
    WHERE [System.Parent] IN (1234, 1235, 1236) ORDER BY [System.Id]
    

Basic Query Syntax

az boards query --wiql "SELECT [fields] FROM workitems WHERE [conditions]" -o table

Verified Working Examples

Query all work items in project

az boards query --wiql "SELECT [System.Id], [System.Title], [System.State] FROM workitems WHERE [System.TeamProject] = 'ProjectName'" -o table

Query by state

az boards query --wiql "SELECT [System.Id], [System.Title] FROM workitems WHERE [System.State] = 'In Progress' AND [System.TeamProject] = 'ProjectName'" -o table

Query by work item type

az boards query --wiql "SELECT [System.Id], [System.Title], [System.State] FROM workitems WHERE [System.WorkItemType] = 'Bug' AND [System.TeamProject] = 'ProjectName'" -o table

Query by assignee

az boards query --wiql "SELECT [System.Id], [System.Title] FROM workitems WHERE [System.AssignedTo] = '[email protected]' AND [System.TeamProject] = 'ProjectName'" -o table

Read the full file on GitHub · 172 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. 10d ago First seen · 172 lines · 93 tokens per session scan A 6611e9f8c6b5

Subscribe to this mod's changes

wiql-queries is a skill published in the GitHub repository JoshuaRamirez/ms-ado-az-claude-code-plugin (5 stars, last pushed 6d ago), licensed MIT. It adds 93 tokens to every session and 1,766 once invoked, about $0.0005 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 2026-08-31.

Related

Other skills, from other repositories