azure-dev: Skill for Claude Code

.github/skills/changelog-generation/SKILL.md

changelog-generation is a skill for Claude Code, Codex from Azure/azure-dev. It costs 167 tokens per session (1,932 once invoked), scanned A, original, MIT.

A release-note workflow for azd, a command-line development tool, and its extensions. It reviews merged GitHub pull requests, groups their changes, updates the version, and writes a changelog.

In plain words
What is it for?
Use it to prepare a core azd or extension release by identifying the scope, selecting the version, classifying merged changes, updating release files, and checking the resulting text.
Why use it?
It helps produce consistent user-facing release notes from completed work instead of manually reconstructing changes from memory. It also checks that the expected release files exist.

Skill for Claude CodeCodex ✓ vendor

Written for no agent in particular: nothing here depends on one.

This is Azure/azure-dev's own configuration. It tells Claude Code and Codex how to work on azure-dev itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything azure-dev configures →

About the project

Azure Developer CLI (azd) is a command-line tool for building, deploying, and operating applications on Azure. Developers use it to move through application workflows such as coding, building, deployment, and monitoring with Azure templates and resources. Its catalogue entries help AI agents work with azd and Azure application projects.

Azure/azure-dev · 570 stars · on GitHub · aka.ms

Reuse

Borrowing it

Nothing to install: this file belongs to Azure/azure-dev. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Azure/azure-dev/main/.github/skills/changelog-generation/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Azure/azure-dev

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 changelog-generation

README.md
[![agentmods](https://agentmods.dev/badge/skills/azure/azure-dev/changelog-generation/github.svg)](https://agentmods.dev/skills/azure/azure-dev/changelog-generation)
Your own site
<a href="https://agentmods.dev/skills/azure/azure-dev/changelog-generation"><img src="https://agentmods.dev/badge/skills/azure/azure-dev/changelog-generation/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 changelog-generation

Your own site · 80×15
<a href="https://agentmods.dev/skills/azure/azure-dev/changelog-generation"><img src="https://agentmods.dev/badge/skills/azure/azure-dev/changelog-generation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 167 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,932 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00167 $0.01932
Opus 5.5 $0.00067 $0.00773
Sonnet 5.5 $0.00033 $0.00386
Haiku 4.5 $0.00017 $0.00193

Measured 29d ago against content hash 1eb797e7857f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

changelog-generation 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 29d 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.

.github/skills/changelog-generation/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

changelog-generation

WORKFLOW SKILL — Generates release changelog entries for azd core or extensions.

INVOKES: GitHub MCP tools, git CLI, gh CLI, cspell CLI, ask_user.

Workflow

Step 1 — Determine Scope

Auto-detect scope from the current working directory:

  1. Check if the cwd is inside a cli/azd/extensions/<name>/ directory.

    • If yes → infer extension scope, with <name> as the target extension.
    • If no → infer core scope.
  2. Present the detected scope to the user for confirmation via ask_user:

    I detected you're in <cwd>, so I'll generate changelog for [core azd CLI | extension <name>]. Is that correct?

    Choices:

    • Yes, that's correct (Recommended)
    • No, switch to [core | an extension]
  3. If extension and not auto-detected: list folders under cli/azd/extensions/ and ask the user to select the target.

  4. After extension scope is confirmed (whether auto-detected or manually selected), verify the target extension contains CHANGELOG.md, version.txt, and extension.yaml. If any are missing, stop and list which files are absent.

Step 2 — Find Cutoff & List Commits

Per references/scope-rules.md § Commit Discovery.

  1. Inspect changelog git history to find the cutoff commit SHA.
  2. List commits from cutoff to origin/main (extensions: scoped to extension path).
  3. If >30 commits in the range, display the count and ask the user if they want to see the full list or proceed directly to PR processing.
  4. Present the commit list to the user. This is a manual pre-filter opportunity — ask if any commits should be explicitly included or excluded before automated processing.

Step 3 — Process Each PR

For each commit remaining after the user's pre-filter in Step 2, extract its PR number using the rules in references/pr-processing.md (each commit maps to exactly one canonical PR). Apply the automated exclusion rules and complete the full sub-workflow before moving to the next. Do not batch or abbreviate — and do not skip a PR unless an explicit error-handling rule applies and the user confirms skipping.

Read the full file on GitHub · 116 lines

Files

What ships with it

47 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.

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. 29d ago Changed 1eb797e7857f
  2. 1mo ago First seen · 116 lines · 167 tokens per session scan A 63bd077cbb8e

Subscribe to this mod's changes

changelog-generation is a skill published in the GitHub repository Azure/azure-dev (570 stars, last pushed today), licensed MIT. It adds 167 tokens to every session and 1,932 once invoked, about $0.0007 per session on Opus 5.5. 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.