biome: Skill for Claude Code

.agents/skills/promote-lint-rules/SKILL.md

promote-lint-rules is a skill for Claude Code from biomejs/biome. It costs 47 tokens per session (820 once invoked), scanned A, original, Apache-2.0.

A workflow for moving Biome lint rules from experimental nursery groups into stable groups. A linter checks source code for problems or unwanted patterns without running the program.

In plain words
What is it for?
It helps verify rules, build a promotion manifest and apply names, groups, recommendations, severities and other requested metadata changes in a batch.
Why use it?
It prevents incomplete promotion requirements, incorrect metadata and inconsistent repeated commands from changing the ruleset.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: installed under .agents/ (shared by several agents).

This is biomejs/biome's own configuration. It tells Claude Code 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/promote-lint-rules/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/biomejs/biome

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 promote-lint-rules

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/biomejs/biome/promote-lint-rules"><img src="https://agentmods.dev/badge/skills/biomejs/biome/promote-lint-rules.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 820 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 $0.00047 $0.00820
Opus 5.5 $0.00019 $0.00328
Sonnet 5.5 $0.00009 $0.00164
Haiku 4.5 $0.00005 $0.00082

Measured 22d ago against content hash 0d73b4c529a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

promote-lint-rules 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/promote-lint-rules/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Promote Lint Rules

Use the batch promotion task instead of invoking just move-rule repeatedly.

Build the Manifest

  1. Read the complete requirements. For a GitHub issue, read both its body and comments.
  2. Verify every listed current rule exists under a crates/biome_*_analyze/src/lint/nursery/ directory.
  3. Resolve incomplete or malformed requirements before editing. Do not infer missing group, recommendation, severity, or rename decisions from neighboring rows.
  4. Create a temporary JSON file outside the repository, such as /tmp/biome-rule-promotions.json.

The top-level object maps each current lower-camel-case rule name to its final stable metadata:

{
  "noCurrentRule": {
    "group": "correctness",
    "recommended": true,
    "severity": "error",
    "newName": "noRenamedRule"
  },
  "useAnotherRule": {
    "group": "style",
    "recommended": false
  }
}

Fields:

  • group is required and must be a11y, complexity, correctness, performance, security, style, or suspicious.
  • recommended is optional. Include it when the requirements specify the final recommendation status; both true and false are meaningful.
  • severity is optional. Accepted values are info, warn, and error. Include it when the requirements specify a new final severity.
  • newName is optional. Omit it when the rule keeps its current name.

Use current names as object keys, even when newName is present. A rule implemented by multiple analyzers, such as matching JavaScript and HTML rules, needs only one entry.

Apply the Plan

Run the task once:

just promote-rules /tmp/biome-rule-promotions.json

The task validates the complete manifest before moving files. It updates declarations, diagnostic categories, fixture option files, rule-option modules, and the migration rename table as applicable. It does not regenerate derived files or snapshots.

Inspect the move before generation:

git status --short
git diff --stat

Read the full file on GitHub · 92 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 First seen · 92 lines · 47 tokens per session scan A 0d73b4c529a5

Subscribe to this mod's changes

promote-lint-rules is a skill published in the GitHub repository biomejs/biome (26,016 stars, last pushed today), licensed Apache-2.0. It adds 47 tokens to every session and 820 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 2026-10-07.