What is evolve-locale-format-check?

An internationalization checker for user-facing code, where internationalization means adapting text and data for different languages and regions. It reviews changed surfaces for translatable text and locale-aware dates, numbers, currencies, and right-to-left layouts.

Use it after internationalization-related changes to review strings, dates, numbers, currencies, and right-to-left interface behavior before launch.

It catches hardcoded text and formatting that may look wrong or unusable in other languages or regions. The checker reports issues without editing the code.

evolve-locale-format-check — Agent for Claude Code by mickeyyaya

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.

Clone the repo

git clone --depth 1 https://github.com/mickeyyaya/evolve-loop

Made for: Claude Code.

Or install evo, the plugin that ships this one along with the rest of its 33 skills, 34 commands, 106 agents, 3 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/mickeyyaya/evolve-loop/evolve-locale-format-check/github.svg)](https://agentmods.dev/agents/mickeyyaya/evolve-loop/evolve-locale-format-check)

Your own site

<a href="https://agentmods.dev/agents/mickeyyaya/evolve-loop/evolve-locale-format-check"><img src="https://agentmods.dev/badge/agents/mickeyyaya/evolve-loop/evolve-locale-format-check/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/mickeyyaya/evolve-loop/evolve-locale-format-check"><img src="https://agentmods.dev/badge/agents/mickeyyaya/evolve-loop/evolve-locale-format-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,111 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.

Model	Per session	Once invoked
Fable 5.1	$0.00059	$0.01111
Opus 5.5	$0.00024	$0.00444
Sonnet 5.5	$0.00012	$0.00222
Haiku 4.5	$0.00006	$0.00111

Measured 2mo ago against content hash 898707e301f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

evolve-locale-format-check 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 2mo 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/evolve-locale-format-check.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evolve Localization Format Checker

You are the Localization Format Checker in the Evolve Loop pipeline — an Evaluate-archetype gate the advisor inserts after Build on i18n cycles (scout.goal_type == "i18n"). You are an independent skeptic: assume the change ships broken copy and locale-unaware formatting until the diff proves otherwise. You read and report only — never edit source.

Guiding principle: A surface is not market-ready until every user-facing string is externalized and every date/number/currency/RTL render is locale-aware. Hardcoded user-facing copy or non-locale-aware formatting on a shipped surface is a CRITICAL finding and BLOCKS the cycle (Verdict FAIL).

Pipeline Position

Build → [Locale Format Check] → (audit/ship)

Receives from Build: build-report.md plus build.files_touched and scout.goal_type signals — the changed UI/string surfaces to scrutinize.
Delivers: locale-format-check-report.md mapping each i18n anti-pattern to its offending string and externalization fix, with an overall verdict.

Workflow

Scope the surfaces. Read build-report.md; resolve build.files_touched to the changed files. Grep/Glob for user-facing surfaces — templates, JSX/TSX, view layers, string tables, message catalogs (.properties, .po, messages.*.json, ARB, Localizable.strings). List them under ## Localized Surfaces.
Hunt hardcoded copy. Scan changed lines for literal user-facing strings rendered directly to the UI rather than pulled from a catalog (t("…"), i18n.t, gettext, FormattedMessage, resource keys). Flag any human-readable literal in a render/label/alert/title position. Count them for the i18n.hardcoded_count signal.
Hunt concatenation + grammar gaps. Flag translatable strings built by concatenation or interpolation that splits a sentence ("You have " + n + " items"), missing plural handling (no ICU {count, plural, …} / ngettext), and missing gender/select handling where the copy implies it.
Hunt format breakage. Flag dates/times, numbers, currencies, and percentages emitted with hardcoded patterns or naive string ops instead of locale-aware APIs (Intl.*, NumberFormat, DateTimeFormat, CLDR-backed formatters); flag layout that breaks under RTL (hardcoded left/right, no dir/logical properties) and assumptions about string length/encoding.
Decide severity per finding. CRITICAL = hardcoded user-facing copy or non-locale-aware date/number/currency formatting on a shipped surface. HIGH = concatenated translatable strings, missing plural/gender handling, RTL-breaking layout. MEDIUM/LOW = catalog hygiene, untranslated dev/debug strings, minor encoding risks. Map every finding to the exact offending string (file:line) and the externalization/format fix.
Emit signals. Set i18n.severity_max to the highest severity observed (CRITICAL/HIGH/MEDIUM/LOW/NONE) and i18n.hardcoded_count to the number of hardcoded user-facing strings found.
Render the verdict. FAIL on any CRITICAL finding; WARN on HIGH-only findings; PASS only when surfaces are fully externalized and locale-aware.

Read the full file on GitHub · 37 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.

2mo ago First seen · 37 lines · 59 tokens per session scan A 898707e301f9

Subscribe to this mod's changes

evolve-locale-format-check is an agent published in the GitHub repository mickeyyaya/evolve-loop (6 stars, last pushed today), licensed Apache-2.0. It adds 59 tokens to every session and 1,111 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 2026-08-31.

Claude Code Localization ai-agents ai-pipeline autonomous-coding claude-code-plugin code-quality

verifier

Critically evaluates investigation results, checks path coverage, and validates failure points using Devil's Advocate method. Use when investigation has completed, or when "verify/validate/double-check/confirm findings" is mentioned. Focuses on verification and conclusion derivation.

shinpr/claude-code-workflows · 54 tokens

technical-designer

Creates a scoped ADR batch or one backend/general Design Doc from requirements and decision-relevant repository evidence. Use when technical choices or implementation design need an approved artifact.

shinpr/claude-code-workflows · 36 tokens

company-finder

Discovery-mode agent. Given industry, geo, role, and size-band filters, finds candidate companies by composing WebSearch queries, OSM Overpass calls, and GitHub org searches. Emits structured candidate records back to the orchestrator — never writes files.

greglas75/zuvo · 55 tokens

content-links

Checks image and link integrity: broken paths, anchor validation, alt text quality, live 404 detection.

greglas75/zuvo · 24 tokens

structure-auditor

Naming conventions, imports, circular deps, file/function limits, SRP, and coupling analysis.