starling: Skill for Claude Code

.agents/skills/writing-style/SKILL.md

writing-style is a skill for Claude Code, Codex from starling-browser/starling. It costs 185 tokens per session (893 once invoked), scanned A, original, Apache-2.0.

A set of plain-language writing rules for prose written in a software project.

In plain words
What is it for?
Use it when writing or reviewing README files, design documents, code comments for people, commit messages, pull requests, and status updates.
Why use it?
It keeps documentation and project messages short, clear, consistent, and easy to read.

Skill for Claude CodeCodex

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

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

Reuse

Borrowing it

Nothing to install: this file belongs to starling-browser/starling. 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/starling-browser/starling/main/.agents/skills/writing-style/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/starling-browser/starling

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 writing-style

README.md
[![agentmods](https://agentmods.dev/badge/skills/starling-browser/starling/writing-style/github.svg)](https://agentmods.dev/skills/starling-browser/starling/writing-style)
Your own site
<a href="https://agentmods.dev/skills/starling-browser/starling/writing-style"><img src="https://agentmods.dev/badge/skills/starling-browser/starling/writing-style/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 writing-style

Your own site · 80×15
<a href="https://agentmods.dev/skills/starling-browser/starling/writing-style"><img src="https://agentmods.dev/badge/skills/starling-browser/starling/writing-style.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 185 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 893 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 $0.00185 $0.00893
Opus 5 $0.00093 $0.00447
Sonnet 5 $0.00037 $0.00179
Haiku 4.5 $0.00018 $0.00089

Measured 9d ago against content hash 3660b706cd77, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

writing-style 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.

.agents/skills/writing-style/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writing style

Apply these rules to every paragraph of prose authored in this project.

Rules

  1. Fifth-grade reading level where possible. Short sentences. Common words. Grammatically correct. Prefer "uses" over "leverages", "checks" over "verifies", "real sites" over "real-world bundles".
  2. No unclear abbreviations. Spell out anything most readers won't know on first use.
    • Fine as-is in context: HTTP, TLS, DNS, URL, DOM, CSS, JSON, PR, CI, GUI, Test262, WPT (when context is clear), HTML, JS, MCP, OTEL, OTLP.
    • Spell out or rephrase: TDZ, SSIM ("similarity score"), PSL ("Public Suffix List"), ALPN (drop or explain), HSTS (drop or "hardening"), GA/gtag ("Google Analytics"), VM ("virtual machine") on first use, GC ("garbage collector") on first use, BCL (".NET base class library").
  3. No semicolons unless truly necessary. A period almost always reads better. Exception: dense table cells where two clauses must share one row.
  4. No verbose explanations. If a sentence restates the previous one with different words, cut it. If a parenthetical is more than ~6 words, ask whether it earns its keep.
  5. Don't point out the obvious.
    • Bad: "runs on every PR" (already in the CI config).
    • Bad: "click the link to learn more" (the link does that).
    • Bad: "these tests pin behavior" right after listing the tests.
    • Bad: filler lead-ins like "These tests are author-written" that add no information.
  6. Never use the phrase "hand-written" — code comments, READMEs, commit messages, anywhere. Name the Starling resource explicitly: "the Starling JS engine", "Starling DOM", "Starling networking from System.Net.Sockets up". Reads as marketing and obscures what we actually mean.

Workflow when invoked

  1. Before writing: scan the rules above.
  2. Draft the prose.
  3. Re-read each paragraph and check:
    • Would a smart fifth grader understand this?
    • Any semicolons I can replace with a period?
    • Any abbreviation a first-time reader wouldn't know?
    • Did I restate the previous sentence?
    • Did I state something the reader can already see (link, code, filename)?
    • Did I write "hand-written" anywhere?
  4. Cut, swap, simplify. Then save.

Read the full file on GitHub · 72 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. 9d ago First seen · 72 lines · 185 tokens per session scan A 3660b706cd77

Subscribe to this mod's changes

writing-style is a skill published in the GitHub repository starling-browser/starling (57 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 185 tokens to every session and 893 once invoked, about $0.0009 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

popular-web-designs

54 real design systems (Stripe, Linear, Vercel) as HTML/CSS.

NousResearch/hermes-agent · 23 tokens

reimagine-it

Content-Derived Design — reads existing HTML and writes a stronger standalone page from headings, facts, names, dates, numbers, links, emails, and colors already in that file. CLI: npx reimagine-it --auto -i page.html -o out.html; also variations, lock, and audit. Use when the user says /reimagine-it, "reimagine it"…

Kayforkind/reimagine-it · 230 tokens

sharpmap

Use when rendering 2D maps in legacy .NET WinForms or ASP.NET WebForms applications. SharpMap: an older .NET 2D mapping library. For new projects, prefer Mapsui.

znlgis/opengis-skills · 44 tokens

preline-mcp

Add, integrate, or build Preline UI components and blocks into HTML files via the Preline MCP server. Use when the user mentions "preline", says "/preline", asks to add a UI component, or requests a Preline block (a ready-made page section) using Preline UI.

htmlstreamofficial/preline · 66 tokens

pdf-press

Teaches agents how to generate Markdown, HTML (with embedded SVG), and Mermaid content that renders beautifully to multi-page PDF via writepdf, with proper page breaks, compact professional layouts, brand and domain-adaptive color schemes, multi-column support for scientific papers, magazine-style editorial documents…

kdcube/kdcube · 74 tokens

preline-theme-generator

Generate, preview, save, or validate Preline theme CSS using the bundled local generator in this skill. Use when the user asks to create a new Preline theme, match a brand color, translate a mood into a theme, generate light and dark theme CSS, preview theme output without writing files, or review and fix generated…

htmlstreamofficial/preline · 89 tokens