localize

A command that adapts marketing content for different languages and markets. It changes wording, tone, idioms, units, currency, and length to fit each locale instead of translating word for word.

In plain words
What is it for?
Localizing content into selected locales, checking each version against market-specific rules, and optionally preparing literal back-translations for approval.
Why use it?
It helps teams produce market-appropriate content while preserving brand rules and terms that must not be translated.

Command

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.

agentmods
npx agentmods add commands/localplugins/plugins/localize
Clone the repo
git clone --depth 1 https://github.com/localplugins/plugins
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 348 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00017 $0.00348
Opus 5 $0.00009 $0.00174
Sonnet 5 $0.00003 $0.00070
Haiku 4.5 $0.00002 $0.00035

Measured yesterday against content hash 84bd3e236463, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

localize 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 yesterday.

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.

content-multiplier/commands/localize.md · 23 lines

What it actually says

Localize

Adapt existing marketing content to other markets using transcreation (not literal translation). Reads only provided content; writes files; no network.

Arguments: $ARGUMENTS

Workflow

  1. Parse args. Identify the source content and required --locales; note --brand and whether --back-translation was requested.
  2. Load the base brand profile and, for each locale, any content/brand/locales/<xx-XX>/ (or branded) overrides.
  3. Transcreate. For each locale, apply the transcreation skill: adapt message, tone, idioms, formality, units/currency, and channel character limits; never translate the do-not-translate glossary terms.
  4. Guard. Send each localized asset to the brand-guardian subagent using that locale's rules (compliance can differ by market); apply corrections.
  5. Back-translation (if --back-translation). For each localized asset, also produce a literal back-translation plus a short note on adaptation choices, for approver sign-off.
  6. Write output to content/output/<slug>/<locale>/… mirroring the source filenames, plus an index.md listing each locale, asset, compliance status, and (if requested) a link to its back-translation.

Never auto-post. Never access the network.

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. yesterday First seen · 23 lines · 17 tokens per session scan A 84bd3e236463

Subscribe to this mod's changes

localize is a command published in the GitHub repository localplugins/plugins (5 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 348 once invoked, about $0.0001 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.