changelog-generator

changelog-generator is a skill for Claude Code, Codex from canonical/copilot-collections. It costs 45 tokens per session (2,474 once invoked), scanned A, original, Apache-2.0.

A release-note tool that turns Git history and pull requests into structured changelogs. It can understand Conventional Commits, a commit-message format with standard change labels.

In plain words
What is it for?
Use it to prepare release notes, compare versions between tags or branches, or maintain a CHANGELOG.md file.
Why use it?
It removes the need to turn noisy commit logs into readable summaries by hand.

Skill for Claude CodeCodex ✓ vendor

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

Good fit Use it to prepare release notes, compare versions between tags or branches, or maintain a CHANGELOG.md file.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/canonical/copilot-collections/changelog-generator
About the project

Canonical Copilot Collections is a repository for organizing and distributing GitHub Copilot instructions, prompts, agents, and skills across Canonical repositories. Teams configure repositories to subscribe to shared collections, such as Python, documentation, or Juju development guidance, and keep those assets synchronized.

canonical/copilot-collections · 29 stars · on GitHub

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 canonical/copilot-collections --skill changelog-generator
Clone the repo
git clone --depth 1 https://github.com/canonical/copilot-collections

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-generator

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/canonical/copilot-collections/changelog-generator"><img src="https://agentmods.dev/badge/skills/canonical/copilot-collections/changelog-generator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,474 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 $0.00045 $0.02474
Opus 5 $0.00023 $0.01237
Sonnet 5 $0.00009 $0.00495
Haiku 4.5 $0.00005 $0.00247

Measured 10d ago against content hash 64742ec6e45b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

changelog-generator 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/changelog-generator/SKILL.md · 328 lines

How it starts

The opening of the file, as written. The whole thing — 328 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Changelog Generator

Guiding Principles

This skill follows these guiding principles:

  1. Changelogs are for humans, not machines. Write entries that a user or operator can understand without reading source code.
  2. There should be an entry for every single version. Never skip a release.
  3. The same types of changes should be grouped. Use the standard categories.
  4. Versions and sections should be linkable. Use reference-style links.
  5. The latest version comes first. Reverse chronological order.
  6. The release date of each version is displayed. ISO 8601 (YYYY-MM-DD).
  7. Mention whether the project follows Semantic Versioning. Include in preamble.

Persona

You are a release engineer responsible for producing clear, audience-appropriate changelogs. You write for users and operators — not developers. You curate notable changes; you do not dump a commit log.


Anti-Patterns (Never Do)

These produce bad changelogs:

  • Commit log diffs — Raw git log output is full of noise (merge commits, obscure titles, internal refactors). A changelog entry documents the noteworthy difference across multiple commits, communicated clearly.
  • Ignoring deprecations — Always surface deprecations, removals, and breaking changes. Users need a clear upgrade path.
  • Confusing dates — Always use ISO 8601 (2026-07-29). Never use regional formats like 07/29/2026 or 29/07/2026.
  • Inconsistent changes — If you mention some changes, mention all notable ones. A partial changelog misleads users into thinking it is complete.

When to Use

  • Preparing release notes for a new tag/version.
  • Summarizing changes between two refs (tags, branches, SHAs).
  • Updating or creating a CHANGELOG.md file.
  • Generating release body text for GitHub Releases.
  • Moving entries from [Unreleased] into a new version at release time.

Inputs

The user provides one or more of:

Input Example Required
Version/tag to release v1.4.0 Yes (or Unreleased)
Base ref (previous version) v1.3.0 or auto-detect from latest tag No
Target ref HEAD, branch name No (defaults to HEAD)
Scope filter Path prefix or package name No
Output format standard, github-release, plain No (defaults to standard)

Read the full file on GitHub · 328 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 · 328 lines · 45 tokens per session scan A 64742ec6e45b

Subscribe to this mod's changes

changelog-generator is a skill published in the GitHub repository canonical/copilot-collections (29 stars, last pushed 7d ago), licensed Apache-2.0. It adds 45 tokens to every session and 2,474 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.

Related

Other skills, from other repositories