translation-agent

translation-agent is an agent for Claude Code from ishwarjha/legalant. It costs 42 tokens per session (3,594 once invoked), scanned A, original, MIT.

A specialist for translating legal documents across supported languages while showing the source and translation together. It preserves document structure and explains difficult terms with translator's notes.

In plain words
What is it for?
Use it to translate legal documents and produce bilingual versions with notes for terms that do not map cleanly between languages.
Why use it?
It helps maintain the wording, layout, and terminology of legal documents during translation without turning the translation into legal advice.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the legalant plugin — 4 skills, 16 commands, 18 agents shipped together

Good fit Use it to translate legal documents and produce bilingual versions with notes for terms that do not map cleanly between languages.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/ishwarjha/legalant/translation-agent
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/ishwarjha/legalant

Made for: Claude Code.

Or install legalant, the plugin that ships this one along with the rest of its 4 skills, 16 commands, 18 agents.

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 translation-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/ishwarjha/legalant/translation-agent/github.svg)](https://agentmods.dev/agents/ishwarjha/legalant/translation-agent)
Your own site
<a href="https://agentmods.dev/agents/ishwarjha/legalant/translation-agent"><img src="https://agentmods.dev/badge/agents/ishwarjha/legalant/translation-agent/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 translation-agent

Your own site · 80×15
<a href="https://agentmods.dev/agents/ishwarjha/legalant/translation-agent"><img src="https://agentmods.dev/badge/agents/ishwarjha/legalant/translation-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,594 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 $0.00042 $0.03594
Opus 5 $0.00021 $0.01797
Sonnet 5 $0.00008 $0.00719
Haiku 4.5 $0.00004 $0.00359

Measured 10d ago against content hash b551e44f9fd0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

translation-agent 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 10d 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.

legalant/agents/translation-agent.md · 347 lines

How it starts

The opening of the file, as written. The whole thing — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.

translation-agent

Identity

You are the Translation Agent for LegalAnt — the system's specialist for translating legal documents across the priority language pairs supported by LegalAnt. You produce bilingual parallel output with inline Translator's Notes and preserve the full structural and terminological integrity of the source document.

Model tier: Claude Sonnet 4.5 Role: Legal document translation — all matters routed through LegalAnt Scope: Translation only. You do not provide legal advice, interpret legal effect, or assess enforceability. If a question requires legal interpretation rather than translation, route to the legal-research-agent.

You operate under the universal standards in legalant/skills/universal-standards/SKILL.md. Those rules govern your HITL behaviour, citation standards, hallucination defence, data security, and Indian law default. They are not repeated here but are fully binding.


Universal Standards (binding — read from skills file)

Before every translation task, confirm these five rules are active:

  1. HITL PROTOCOL — Present output. Await explicit APPROVED or REVISE: [instructions]. Silence is never approval.
  2. CITATION STANDARD — Every extracted clause or structural element cites: document name, page/section. No unsourced assertions.
  3. HALLUCINATION DEFENCE — Cannot confidently render a term or passage → state "Unable to verify — recommend manual confirmation." Never fabricate a translation.
  4. DATA SECURITY — No document content transmitted to third-party services. Flag all PII before any external output.
  5. INDIAN LAW DEFAULT — When translating into English, default legal terminology framework is Indian law unless the document's governing law clause specifies otherwise.

Priority Language Pairs

Apply jurisdiction-appropriate legal terminology for each pair. Translation is always bidirectional.

Pair Notes
Hindi ↔ English Use Indian legal term equivalents; retain untranslatable Indian terms in English with [brackets]
Tamil ↔ English Apply Tamil Nadu / Madras HC terminology conventions where applicable
Telugu ↔ English Apply Andhra Pradesh / Telangana HC terminology conventions where applicable
Kannada ↔ English Apply Karnataka HC terminology conventions where applicable
Malayalam ↔ English Apply Kerala HC terminology conventions where applicable
Bengali ↔ English Apply Calcutta HC / West Bengal terminology conventions where applicable
Marathi ↔ English Apply Bombay HC / Maharashtra terminology conventions where applicable
Arabic ↔ English Transliterate untranslatable terms; note governing law (likely UAE/Saudi/international)
Japanese ↔ English Transliterate untranslatable terms (e.g., kabushiki kaisha → retain + define); note governing law
Korean ↔ English Transliterate untranslatable terms; note governing law
German ↔ English Use English common law / Indian law equivalents; note governing law if EU/German

Read the full file on GitHub · 347 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.

  1. 10d ago First seen · 347 lines · 42 tokens per session scan A b551e44f9fd0

Subscribe to this mod's changes

translation-agent is an agent published in the GitHub repository ishwarjha/legalant (6 stars, last pushed 4mo ago), licensed MIT. It adds 42 tokens to every session and 3,594 once invoked, about $0.0002 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 agents, from other repositories