claude-translation-agency: Instructions file for Claude Code

CLAUDE.md

claude-translation-agency CLAUDE.md is an instructions file for Claude Code from roshaw/claude-translation-agency. It costs 7,709 tokens per session, scanned A, original, MIT.

A reusable system for translating projects or files into other languages, with three rounds of writing and review. It can be used for websites, plugins, documentation, apps, or data files.

In plain words
What is it for?
Use it to localize websites, WordPress plugins, React app text, Markdown documents, or JSON files into a chosen language and subject area.
Why use it?
It helps catch common translation problems such as leftover source text, inconsistent terms, missing placeholders, and broken markup. Separate review rounds provide checks beyond a single translator’s pass.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md.

This is roshaw/claude-translation-agency's own configuration. It tells Claude Code how to work on claude-translation-agency itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-translation-agency configures →

Reuse

Borrowing it

Nothing to install: this file belongs to roshaw/claude-translation-agency. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/roshaw/claude-translation-agency/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/roshaw/claude-translation-agency

Made for: Claude Code.

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 claude-translation-agency CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/roshaw/claude-translation-agency/claude-md/github.svg)](https://agentmods.dev/instructions/roshaw/claude-translation-agency/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/roshaw/claude-translation-agency/claude-md"><img src="https://agentmods.dev/badge/instructions/roshaw/claude-translation-agency/claude-md/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 claude-translation-agency CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/roshaw/claude-translation-agency/claude-md"><img src="https://agentmods.dev/badge/instructions/roshaw/claude-translation-agency/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 7,709 This file is loaded in full into every session.
When invoked 7,709 The same file — it is already loaded in full.
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 $0.07709 $0.07709
Opus 5 $0.03854 $0.03854
Sonnet 5 $0.01542 $0.01542
Haiku 4.5 $0.00771 $0.00771

Measured 12d ago against content hash 6c25da14be34, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

claude-translation-agency CLAUDE.md 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 12d 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.

CLAUDE.md · 453 lines

How it starts

The opening of the file, as written. The whole thing — 453 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Translation Agency

Version 2.1.0 · MIT licensed · SemVer + CHANGELOG.md

A reusable, project-agnostic translation system: ready-to-use skills and agents that translate any project or set of files into any language, with a domain specialization you choose per run (or leave at the general default).

It was extracted and generalized from a production legal-fee-calculator localization pipeline (Tarifo.net), whose three-tier translator panel and adversarial-QA design proved out over many real passes. The Tarifo-specific hardwiring (its file layout, its legal domain, its git/deploy rules) has been lifted out into settings, so the same machinery now works on a WordPress plugin, a folder of Markdown docs, a React app's i18n, or a batch of JSON files.

The model: a three-tier translator panel

Every translation run is orchestrated by a panel of three agents, mirroring a real localization agency (worker → senior → lead), because a single-writer flow reliably leaks a known set of errors (source-language leftovers, wrong terminology, dropped placeholders, broken markup, and the writer's own "looks clean to me" blind spots). Splitting writing from adversarial review is what catches them.

  • Lead.claude/agents/translate-lead.md (Opus). Project manager. Spawned once per run; plans batches, dispatches each to a worker, and adversarially reviews every result against a fixed C1–C7 checklist before signing off. Runs final blind-spot sweeps. Loads the run's specialization so its terminology check is domain-aware. Not a translator itself.
  • Senior.claude/agents/translate-senior.md (Sonnet). Translates domain-prose and any substantive surface (documents, marketing/legal/technical copy, message values, MDX/HTML, WordPress .po). Spawned by the Lead.
  • Junior.claude/agents/translate-junior.md (Haiku). Translates only low-risk UI chrome (nav, buttons, footer, generic errors). Cheap by design; escalates anything domain-critical to the Senior. Spawned by the Lead.

Read the full file on GitHub · 453 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. 12d ago First seen · 453 lines · 7,709 tokens per session scan A 6c25da14be34

Subscribe to this mod's changes

claude-translation-agency CLAUDE.md is an instructions file published in the GitHub repository roshaw/claude-translation-agency (2 stars, last pushed 15d ago), licensed MIT. It adds 7,709 tokens to every session, about $0.0385 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 instructions, from other repositories

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,126 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens