biome: Skill for Claude Code

.agents/skills/changeset/SKILL.md

changeset is a skill for Claude Code, Codex from biomejs/biome. It costs 54 tokens per session (734 once invoked), scanned A, original, Apache-2.0.

Guidance for deciding whether a code change needs a changeset, a short release-note file that records user-visible changes, and for choosing its release level.

In plain words
What is it for?
Use it after changes to a CLI, library, parser, formatter, linter, diagnostic, or assist to classify the change and create the required .changeset Markdown file.
Why use it?
It prevents teams from missing release notes or assigning the wrong patch, minor, or major version impact.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is biomejs/biome's own configuration. It tells Claude Code and Codex how to work on biome 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 biome configures →

About the project

Biome is a web-development toolchain that formats and checks source code for languages such as JavaScript, TypeScript, JSX, and CSS. Developers use its command-line and language-server interfaces to maintain code quality in web projects. Catalogue add-ons extend workflows around the toolchain.

biomejs/biome · 26,016 stars · on GitHub · biomejs.dev

Reuse

Borrowing it

Nothing to install: this file belongs to biomejs/biome. 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/biomejs/biome/main/.agents/skills/changeset/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/biomejs/biome

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 changeset

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/biomejs/biome/changeset"><img src="https://agentmods.dev/badge/skills/biomejs/biome/changeset.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 734 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
  • Snyk pass 7 Sept 2026
  • 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 $0.00054 $0.00734
Opus 5.5 $0.00022 $0.00294
Sonnet 5.5 $0.00011 $0.00147
Haiku 4.5 $0.00005 $0.00073

Measured 22d ago against content hash 9f8f1cd2fb7d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

changeset 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 22d 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.

.agents/skills/changeset/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Changesets

Changesets describe user-visible behavior for release notes. Root AGENTS.md defines when automated contributions require one; CONTRIBUTING.md is canonical for package selection, versioning, branch targets, and prose format.

Decide Whether One Is Required

A changeset is required for behavior visible to users of the CLI, libraries, published crates, diagnostics, parser, formatter, linter, or assists.

No changeset is needed for an internal refactor with identical behavior, tests only, CI/build maintenance, or documentation-only edits.

Before opening a PR, explicitly confirm the user-facing classification as required by AGENTS.md. Do not infer user visibility only from the files changed.

Choose the Release Level

Change Level Target
Bug fix or non-breaking behavior correction patch main
New nursery lint rule patch main
New user-facing feature or nursery promotion minor next
Breaking user API change major next

Nursery rules are the exception to the usual new-feature mapping because they do not follow semantic versioning. Verify unusual cases against the current versioning policy.

Create the File

Run just new-changeset-empty to generate an empty file.

just new-changeset-empty

An empty generated entry starts with frontmatter delimiters. Replace that frontmatter with the package and release level rather than appending a second block:

---
"@biomejs/biome": patch
---

Description.

Use #### or ##### for headings inside a longer entry. Other heading levels interfere with changelog generation.

Write the Entry

  • Describe user-visible behavior, not implementation.
  • Use one to three sentences unless the impact genuinely needs an example.
  • Use past tense for the contribution and present tense for resulting Biome behavior.
  • Start bug fixes with the linked issue when one exists. If a link doesn't exist, start with a verb.
  • Link rule and assist names to their Biome website pages.
  • End every sentence with a full stop.

Read the full file on GitHub · 83 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. 22d ago Changed 9f8f1cd2fb7d
  2. 1mo ago First seen · 83 lines · 54 tokens per session scan A 1aaf64cff074

Subscribe to this mod's changes

changeset is a skill published in the GitHub repository biomejs/biome (26,016 stars, last pushed today), licensed Apache-2.0. It adds 54 tokens to every session and 734 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

Biome

Biome 2.x — fast all-in-one web toolchain in Rust. Formats, lints, assists. Replaces Prettier + ESLint.

pledgeandgrow/pledge-skills · 33 tokens

prettier-docs

Prettier 3.9.5 — opinionated code formatter. CLI, API, config, plugins, editor integration, CI.

pledgeandgrow/pledge-skills · 34 tokens

draft-release-notes

Author the committed release-notes file for a Prisma 8 release (stable or 8.0.0-rc.N) by enumerating the merged PRs since the previous release v tag (stable or -rc.N), resolving opaque TML-NNNN: titles via Linear context (never copied verbatim), triaging public-worthiness, and writing categorized notes — breaking…

prisma/orm · 174 tokens

publish-npm-version

Cuts the next release of Prisma 8: bumps the root package.json version (on the v8 RC line: 8.0.0-rc.N → rc.N+1), propagates it to every workspace package, and opens a PR titled "chore(release): bump to ". When the maintainer merges the PR, the Publish to npm workflow runs automatically and ships the new version to npm…

prisma/orm · 182 tokens

hero-diff-highlight

A dark code editor reveals a red deletion then a green addition with a soft pulse. Function: PR / code-change explainer.

Unclecheng-li/AI_Animation · 0 tokens

playground-snapshot-release

Publish a Playground UI snapshot (@mastra/playground-ui and its workspace dependencies) from main or the current branch via the playground-snapshot mode of the Publish to npm workflow, wait for it to finish, then open a PR on mastra-ai/platform bumping the frontend to the published snapshot version. Use when asked to…

mastra-ai/mastra · 96 tokens