audit-sprint-ado

audit-sprint-ado is a skill for Claude Code, Codex from abrahamFerga/scrum-skills. It costs 145 tokens per session (1,616 once invoked), scanned A, original, MIT.

An audit tool for a completed or ongoing Sprint in Azure DevOps, Microsoft's platform for managing software projects. It checks the Sprint Goal, work-item records, progress states, capacity, required fields, and the Definition of Done—the team's agreed completion standard.

In plain words
What is it for?
Use it to review a specific Azure DevOps iteration, inspect its work items and capacity data, and receive an audit summary with findings.
Why use it?
It reveals missing or unreliable project data and practices that can hide progress or distort delivery measures. It reports findings with severity levels so the team can address the most important issues.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code.

Good fit Use it to review a specific Azure DevOps iteration, inspect its work items and capacity data, and receive an audit summary with findings.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/abrahamferga/scrum-skills/audit-sprint-ado
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 abrahamFerga/scrum-skills --skill audit-sprint-ado
Clone the repo
git clone --depth 1 https://github.com/abrahamFerga/scrum-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.

agentmods badge for audit-sprint-ado

README.md
[![agentmods](https://agentmods.dev/badge/skills/abrahamferga/scrum-skills/audit-sprint-ado/github.svg)](https://agentmods.dev/skills/abrahamferga/scrum-skills/audit-sprint-ado)
Your own site
<a href="https://agentmods.dev/skills/abrahamferga/scrum-skills/audit-sprint-ado"><img src="https://agentmods.dev/badge/skills/abrahamferga/scrum-skills/audit-sprint-ado/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 audit-sprint-ado

Your own site · 80×15
<a href="https://agentmods.dev/skills/abrahamferga/scrum-skills/audit-sprint-ado"><img src="https://agentmods.dev/badge/skills/abrahamferga/scrum-skills/audit-sprint-ado.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 145 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,616 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 $0.00145 $0.01616
Opus 5 $0.00072 $0.00808
Sonnet 5 $0.00029 $0.00323
Haiku 4.5 $0.00015 $0.00162

Measured 11d ago against content hash c980e431702e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

audit-sprint-ado 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/audit-sprint-ado/SKILL.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ADO Sprint Audit

Purpose

ADO gives teams enormous flexibility — which means it's easy to drift into habits that obscure progress, hide impediments, or make velocity data meaningless. This audit checks both Scrum health (is the team doing Scrum well?) and ADO hygiene (is the data in the board trustworthy?).


Prerequisites

This skill requires an active Azure DevOps MCP connection. If mcp__azure-devops__* or mcp__ado__* tools are not available, let the user know and stop.


Step 1 — Identify the sprint

Ask: "Which sprint should I audit — the current one, the one just completed, or a specific iteration path?"

Use work_list_team_iterations or work_list_iterations to confirm the iteration path. Store as $ITERATION.


Step 2 — Fetch sprint data

Retrieve all relevant data for $ITERATION:

  • All work items in the iteration via wit_get_work_items_for_iteration
  • Team capacity via work_get_team_capacity or work_get_iteration_capacities
  • Team settings (Definition of Done, working days) via work_get_team_settings

Group items by type: PBI / User Story, Task, Bug, Test Case, other.


Step 3 — Run the audit

Grade each check as:

  • Pass — meets the standard
  • ⚠️ Warning — worth improving
  • Fail — missing or broken; impacts team effectiveness

Area 1 — Sprint Goal (Scrum)

Check Pass condition
Sprint Goal defined Iteration has a non-empty goal field
Sprint Goal is outcome-oriented Goal reads as a value statement, not a task list
All committed items relate to the Sprint Goal No large clusters of work unrelated to the goal

A missing Sprint Goal is a significant Scrum health issue — the team has no way to assess whether the Sprint was successful beyond counting items.

Area 2 — Work Item Hygiene (ADO)

Check Pass condition
All items have an assigned owner No unassigned active or resolved items
All items are linked to the correct iteration No stray items from other iterations
PBIs / User Stories have a parent (Feature or Epic) Orphaned backlog items are harder to trace to strategy
Bugs are linked to the PBI they affect Unlinked bugs obscure the root cause
No items in "Removed" state without a comment Silent removals hide scope changes
Item titles are descriptive No "New PBI", "Task 1", or copy-paste duplicates

Read the full file on GitHub · 159 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. 11d ago First seen · 159 lines · 145 tokens per session scan A c980e431702e

Subscribe to this mod's changes

audit-sprint-ado is a skill published in the GitHub repository abrahamFerga/scrum-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 145 tokens to every session and 1,616 once invoked, about $0.0007 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.