changelog

changelog is a skill for Claude Code from MuhammadUsmanGM/claude-code-best-practices. It costs 46 tokens per session (411 once invoked), scanned A, original, MIT.

A workflow for creating or updating a CHANGELOG.md file, which records user-visible changes between software releases.

In plain words
What is it for?
Use it when preparing a release or summarizing changes since a version tag. It groups commits, follows the existing changelog style, and asks for the release version before writing.
Why use it?
It turns git history into organized release notes and reduces the chance of overlooking important additions, fixes, removals, or security changes.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it when preparing a release or summarizing changes since a version tag. It groups commits, follows the existing changelog style, and asks for the release version before writing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/muhammadusmangm/claude-code-best-practices/changelog
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 MuhammadUsmanGM/claude-code-best-practices --skill changelog
Clone the repo
git clone --depth 1 https://github.com/MuhammadUsmanGM/claude-code-best-practices

Made for: Claude Code.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/muhammadusmangm/claude-code-best-practices/changelog"><img src="https://agentmods.dev/badge/skills/muhammadusmangm/claude-code-best-practices/changelog.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 411 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 $0.00046 $0.00411
Opus 5 $0.00023 $0.00205
Sonnet 5 $0.00009 $0.00082
Haiku 4.5 $0.00005 $0.00041

Measured 9d ago against content hash 46c14bb1c242, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

changelog 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 9d 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.

examples/skills/changelog/SKILL.md · 30 lines

What it actually says

Changelog

Produce or update CHANGELOG.md in the Keep-a-Changelog format.

Steps

  1. git describe --tags --abbrev=0 to find the most recent tag. If no tag exists, use the repo's first commit and tell the user there's no prior tag.
  2. git log <last-tag>..HEAD --oneline --no-merges to enumerate commits.
  3. Read the existing CHANGELOG.md if present. Match its headings, casing, and date format. If missing, create one with the Keep-a-Changelog header.
  4. Group commits into sections — Added, Changed, Fixed, Removed, Deprecated, Security — by inspecting subject prefixes (feat: → Added, fix: → Fixed, refactor:/perf: → Changed, etc.). Merge trivial commits into one bullet.
  5. Ask the user for the new version number (semver). Do not guess.
  6. Insert a new ## [x.y.z] - YYYY-MM-DD section above the previous release. Move "Unreleased" content in if present.
  7. Show the diff before writing. Write only after confirmation.

Rules

  • Rewrite commit subjects into user-facing language. "feat: add FOO" → "Added FOO that does X."
  • Drop internal-only commits (chore(deps), CI-only changes) unless they affect consumers.
  • Do not create a git tag. Do not commit. Hand the finished file back to the user.

Output

Print the new section you added, then stop.

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. 9d ago First seen · 30 lines · 46 tokens per session scan A 46c14bb1c242

Subscribe to this mod's changes

changelog is a skill published in the GitHub repository MuhammadUsmanGM/claude-code-best-practices (79 stars, last pushed 2mo ago), licensed MIT. It adds 46 tokens to every session and 411 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.