bilingual-reader

bilingual-reader is a skill for Claude Code, Codex from surfmind-space/awesome-surfmind. It costs 72 tokens per session (435 once invoked), scanned A, original, MIT.

A translation and explanation helper for selected text. It preserves the original meaning while explaining idioms, cultural references, formality, and phrases that cannot be translated literally.

In plain words
What is it for?
Use it to translate text into another language, clarify difficult phrases, identify key terms, and explain literal traps.
Why use it?
A word-for-word translation can lose tone or produce a misleading meaning, especially for idioms and cultural references.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to translate text into another language, clarify difficult phrases, identify key terms, and explain literal traps.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/surfmind-space/awesome-surfmind/bilingual-reader
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 surfmind-space/awesome-surfmind --skill bilingual-reader
Clone the repo
git clone --depth 1 https://github.com/surfmind-space/awesome-surfmind

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 bilingual-reader

README.md
[![agentmods](https://agentmods.dev/badge/skills/surfmind-space/awesome-surfmind/bilingual-reader.svg)](https://agentmods.dev/skills/surfmind-space/awesome-surfmind/bilingual-reader)
Your own site
<a href="https://agentmods.dev/skills/surfmind-space/awesome-surfmind/bilingual-reader"><img src="https://agentmods.dev/badge/skills/surfmind-space/awesome-surfmind/bilingual-reader.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 435 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 $0.00072 $0.00435
Opus 5 $0.00036 $0.00217
Sonnet 5 $0.00014 $0.00087
Haiku 4.5 $0.00007 $0.00044

Measured 7d ago against content hash 84c77b9f3d47, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

bilingual-reader 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 7d 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.

skills/bilingual-reader/SKILL.md · 35 lines

What it actually says

Bilingual Reader

Translate the selected text into {value} and explain the idioms, cultural references, formality, and terms that do not carry over literally. Translate naturally rather than word-for-word, never flatten an important tone difference, and never invent a meaning for a phrase you cannot read.

  1. Identify the source and target languages; ask if the target is unclear.
  2. Translate the meaning naturally, preserving names, links, numbers, code, dates, currencies, and formatting. Keep product names, code identifiers, and URLs unchanged unless asked.
  3. Explain idioms, cultural references, formality, and terms that do not translate literally — what a literal reading would miss.
  4. When several phrases are tricky, add a short side-by-side table of the original and its natural rendering.

Report a Natural translation, then Nuance notes, Key terms, and Literal traps when they apply. If the text is too short or out of context to read confidently, say what is missing.

Example

Source (French): "Il m'a posé un lapin hier soir."

Natural translation: He stood me up last night.

Nuance notes: Casual, slightly exasperated tone — fits friends or dating, not a formal report.

Key terms: poser un lapin (à quelqu'un) — to fail to show up for a planned meeting.

Literal traps: Word-for-word this reads "he put a rabbit on me," which has nothing to do with rabbits — it's a fixed idiom for missing a date.

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. 7d ago First seen · 35 lines · 72 tokens per session scan A 84c77b9f3d47

Subscribe to this mod's changes

bilingual-reader is a skill published in the GitHub repository surfmind-space/awesome-surfmind (5 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 435 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.