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.
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.
curl -O https://raw.githubusercontent.com/biomejs/biome/main/.agents/skills/formatter-development/SKILL.mdgit clone --depth 1 https://github.com/biomejs/biomeWrote 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.
[](https://agentmods.dev/skills/biomejs/biome/formatter-development)<a href="https://agentmods.dev/skills/biomejs/biome/formatter-development"><img src="https://agentmods.dev/badge/skills/biomejs/biome/formatter-development/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.
<a href="https://agentmods.dev/skills/biomejs/biome/formatter-development"><img src="https://agentmods.dev/badge/skills/biomejs/biome/formatter-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00057 | $0.01723 |
| Opus 5.5 | $0.00023 | $0.00689 |
| Sonnet 5.5 | $0.00011 | $0.00345 |
| Haiku 4.5 | $0.00006 | $0.00172 |
Grade A, and why
formatter-development 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Formatter Development
Use crates/biome_formatter/CONTRIBUTING.md and the language formatter's guide as the canonical architecture references. Inspect neighboring node implementations before selecting IR primitives.
Workflow
- Reproduce the behavior with a focused internal formatter spec or
quick_test. - Inspect the node fields, comments, and nearby formatting rules.
- Implement the smallest layout change using formatter IR.
- Run focused formatter tests and inspect snapshots.
- Compare with Prettier when compatibility is relevant.
- Format and lint before committing.
Printing Discipline
Formatter output is a structured rewrite of the source tree, not a fresh pretty-printer. Treat every missed node, missed token, unchecked suppression, and untracked replacement as a formatter bug, not as style feedback.
- Every source token in the formatted range MUST be consumed exactly once. A token is consumed only by formatting it, removing it with
format_removed, replacing it withformat_replaced, or by a language-specific helper that does one of those operations. - Every source node in the formatted range MUST be handled every time. Prefer
node.format()ornode.format().with_options(...)so the node's own rule formats the node, checks suppressions, and routes comments through the formatter infrastructure. - A parent formatter MUST NOT inline a child node's fields just to get a convenient layout. Move the layout decision into the child rule or pass options into the child formatter.
- If an architecture-specific formatter bypasses a node's rule, it MUST NOT skip the node silently. It MUST check
f.context().comments().is_suppressed(node.syntax()); if the node is suppressed, it MUST write the language'sformat_suppressed_node(...)helper instead of formatting the node body. Without this check, debug builds fail suppression coverage and user suppressions can be ignored. - Source tokens MUST be printed through their typed accessors. Use
token("...")only for syntax inserted by the formatter when no source token exists. - Removing a source token from output MUST use
format_removed(&token). Do not drop the field, bind it to_, or omit it fromwrite!without consuming it throughformat_removed; skipped trivia still belongs to that token. - Replacing a source token's text MUST use
format_replaced(&token, &replacement). Do not print the replacement directly and do not usetoken("...")for replacement text, because the original token still has trivia and must be marked consumed. - Custom formatting MUST be carried by a small struct implementing
Format<Context>. Do not use free functions or stored closure values to carry formatter state or layout invariants. Useformat_withonly for one-off local glue that is immediately written.
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.
- 1mo ago Changed · +15 lines b767e9140192
- 1mo ago Changed · +7 lines · +1 tokens per session 73b9dbd37b58
- 1mo ago First seen · 105 lines · 56 tokens per session scan A b52cda40e3a9
formatter-development is a skill published in the GitHub repository biomejs/biome (26,016 stars, last pushed today), licensed Apache-2.0. It adds 57 tokens to every session and 1,723 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.
Other skills, from other repositories
Biome
Biome 2.x — fast all-in-one web toolchain in Rust. Formats, lints, assists. Replaces Prettier + ESLint.
prettier-docs
Prettier 3.9.5 — opinionated code formatter. CLI, API, config, plugins, editor integration, CI.
migrate-oxfmt
Guide for migrating a project from Prettier or Biome to Oxfmt. Use when asked to migrate, convert, or switch a project's formatter from Prettier or Biome to Oxfmt.
migrate-oxlint
Guide for migrating a project from ESLint to Oxlint. Use when asked to migrate, convert, or switch a JavaScript/TypeScript project's linter from ESLint to Oxlint.
insta-snapshots
Review and update Oxc Insta snapshots non-interactively after expected output changes or snapshot test failures.
performance-lint-rules
Performance review guidance for Oxc linter rule implementations. Use only when reviewing Rust rule code under crates/oxclinter/src/rules/ or when explicitly auditing those rules for performance improvements.