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.
npx skills add sigistry/marketplace --skill icu-messageformatgit clone --depth 1 https://github.com/sigistry/marketplaceWrote 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/sigistry/marketplace/icu-messageformat)<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.
<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>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 | $0.00087 | $0.00903 |
| Opus 5 | $0.00044 | $0.00451 |
| Sonnet 5 | $0.00017 | $0.00181 |
| Haiku 4.5 | $0.00009 | $0.00090 |
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.
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.
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.
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.
- 9d ago First seen · 44 lines · 87 tokens per session scan A a6a29884ebfd
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.
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…
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…
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…
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…
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…
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"…