icu-messageformat

icu-messageformat is a skill for Claude Code from sigistry/marketplace. It costs 87 tokens per session (903 once invoked), scanned A, original, MIT.

A reference for writing ICU MessageFormat, a standard way to put translation rules such as plurals, numbers, dates, and grammatical choices inside one message.

In plain words
What is it for?
Use it when building internationalized applications with libraries such as FormatJS, react-intl, react-i18next, vue-i18n, next-intl, or MessageFormat.js.
Why use it?
It prevents translated sentences from breaking when languages use different word order or plural forms.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the a11y-i18n-remediator plugin — 3 skills, 5 commands, 2 agents, 1 hook shipped together

Good fit Use it when building internationalized applications with libraries such as FormatJS, react-intl, react-i18next, vue-i18n, next-intl, or MessageFormat.js.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sigistry/marketplace/icu-messageformat
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 sigistry/marketplace --skill icu-messageformat
Clone the repo
git clone --depth 1 https://github.com/sigistry/marketplace

Made for: Claude Code.

Or install a11y-i18n-remediator, the plugin that ships this one along with the rest of its 3 skills, 5 commands, 2 agents, 1 hook.

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 icu-messageformat

README.md
[![agentmods](https://agentmods.dev/badge/skills/sigistry/marketplace/icu-messageformat/github.svg)](https://agentmods.dev/skills/sigistry/marketplace/icu-messageformat)
Your own site
<a href="https://agentmods.dev/skills/sigistry/marketplace/icu-messageformat"><img src="https://agentmods.dev/badge/skills/sigistry/marketplace/icu-messageformat/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 icu-messageformat

Your own site · 80×15
<a href="https://agentmods.dev/skills/sigistry/marketplace/icu-messageformat"><img src="https://agentmods.dev/badge/skills/sigistry/marketplace/icu-messageformat.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 903 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 $0.00087 $0.00903
Opus 5 $0.00044 $0.00451
Sonnet 5 $0.00017 $0.00181
Haiku 4.5 $0.00009 $0.00090

Measured 9d ago against content hash a6a29884ebfd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

icu-messageformat 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.

plugins/a11y-i18n-remediator/skills/icu-messageformat/SKILL.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ICU MessageFormat

Purpose

Provide a standardized reference for writing correct ICU MessageFormat, the syntax used by FormatJS/react-intl, react-i18next, vue-i18n, next-intl, and MessageFormat.js, so that translated strings agree grammatically in every target language. The single most common i18n bug is a sentence built by concatenation (count + ' items'); it is untranslatable because other languages inflect the noun, reorder the clause, or need more than two plural forms. ICU solves this by putting the grammar inside the message where translators can adapt it.

The Core Rule: One Message, One Argument

Never split a sentence across strings or build it with +. A quantity, a name, or a gendered choice becomes an argument inside a single message, so the translator controls word order and agreement:

Bad:   t('cart.count') + ' ' + t('cart.items')          // untranslatable
Good:  {count, plural, one {# item} other {# items}}     // translator owns the plural

Argument Types

Form Shape Use for
Simple {name} interpolate a value verbatim
plural {count, plural, one {…} other {…}} count-based noun agreement (cardinal)
selectordinal {n, selectordinal, one {#st} two {#nd} few {#rd} other {#th}} ranks: "1st", "2nd"
select {gender, select, male {he} female {she} other {they}} gender or any enumerated branch
number {price, number, currency} locale-formatted numbers/currency/percent
date / time {when, date, medium} locale-formatted dates/times

Pluralization Is Not Two Forms

English has two cardinal forms (one/other); most languages do not. Arabic uses six (zero, one, two, few, many, other), Polish and Russian use four, Japanese and Chinese use one. You must author every category the source language needs, and never assume other locales copy English's one/other. The # token prints the count in the locale's number format. See references/pluralization-rules.md.

Read the full file on GitHub · 44 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 44 lines · 87 tokens per session scan A a6a29884ebfd

Subscribe to this mod's changes

icu-messageformat is a skill published in the GitHub repository sigistry/marketplace (3 stars, last pushed 5d ago), licensed MIT. It adds 87 tokens to every session and 903 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

design-everyday-things

Apply foundational design principles: affordances, signifiers, constraints, feedback, and conceptual models. Use when the user mentions "why is this confusing", "affordance", "error prevention", "discoverability", "human-centered design", "mental model", "mapping", "seven stages of action", "users keep making…

wondelai/skills · 132 tokens

traction-eos

Implement the Entrepreneurial Operating System (EOS) to align vision and execution across a company. Use when the user mentions "EOS", "Entrepreneurial Operating System", "V/TO", "quarterly rocks", "Level 10 meetings", "accountability chart", "IDS process", "my company feels chaotic", "we keep having the same…

wondelai/skills · 147 tokens

create-app

Guided journey from a raw app idea to a validated, cleanly architected first version that ships on a sustainable cadence. Orchestrates ten skills phase by phase - lean-startup, design-sprint, clean-architecture, domain-driven-design, clean-code, pragmatic-programmer, system-design, ios-hig-design, 37signals-way…

wondelai/skills · 217 tokens

cold-start-problem

Start and scale networked products using Andrew Chen's "The Cold Start Problem" framework for network effects. Use when the user mentions "network effects", "chicken and egg", "cold start", "two-sided marketplace", "atomic network", "hard side", "liquidity", "critical mass", "invite-only launch", "how do I get my…

wondelai/skills · 168 tokens

37signals-way

Build lean, opinionated products using the 37signals philosophy from "Getting Real", "Rework", and "Shape Up". Use when the user mentions "Getting Real", "Rework", "Shape Up", "37signals", "Basecamp method", "six-week cycles", "fixed time variable scope", "appetite vs estimates", "betting table", "breadboarding", "fat…

wondelai/skills · 177 tokens

clean-architecture

Structure software around the Dependency Rule: source code dependencies point inward from frameworks to use cases to entities. Use when the user mentions "architecture layers", "dependency rule", "ports and adapters (hexagonal)", "onion architecture", "screaming architecture", "where should business logic go"…

wondelai/skills · 147 tokens