turjuman: Instructions file for Claude Code

CLAUDE.md

turjuman CLAUDE.md is an instructions file for Claude Code from mogharsallah/turjuman. It costs 2,340 tokens per session, scanned A, original, MIT.

A set of development instructions for Turjuman, a self-hosted translation management system. It uses an AI agent through an MCP server to translate and a developer command-line tool for locale files; locale files hold text for different languages.

In plain words
What is it for?
Guiding development and testing in Turjuman, including its TypeScript packages, AWS services, DynamoDB data store, and LocalStack integration tests.
Why use it?
It gives an AI coding agent the project's architecture, commands, testing layers, and known constraints before it changes code.

Instructions file for Claude Code

Written for Claude Code: PostToolUse hook event. Also seen: reads .claude/ paths.

This is mogharsallah/turjuman's own configuration. It tells Claude Code how to work on turjuman 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 turjuman configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mogharsallah/turjuman. 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/mogharsallah/turjuman/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/mogharsallah/turjuman

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 turjuman CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mogharsallah/turjuman/claude-md"><img src="https://agentmods.dev/badge/instructions/mogharsallah/turjuman/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,340 This file is loaded in full into every session.
When invoked 2,340 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 $0.02340 $0.02340
Opus 5 $0.01170 $0.01170
Sonnet 5 $0.00468 $0.00468
Haiku 4.5 $0.00234 $0.00234

Measured 8d ago against content hash 4bc03dff9ad9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

turjuman 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 8d 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 · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Turjuman is open-source, self-hosted translation management driven primarily through an MCP server (an LLM/agent does the translating) with a thin developer CLI for deterministic locale-file work. It runs serverless on AWS (Lambda Function URLs + a single DynamoDB table). Deliberate non-goals: no web UI, no built-in machine-translation engine, no vendor marketplace (see ROADMAP.md).

Follow YAGNI principles, and one-liner solutions.

Commands

Standard scripts (build, typecheck, test, check, clean, …) live in package.json. The non-obvious invocations:

# Run one package, one file, or one test case (workspaces use plain `vitest run`):
pnpm --filter @turjuman/core run test                          # one package
pnpm --filter @turjuman/core run test -- services.test.ts      # one file (path substring)
pnpm --filter @turjuman/core run test -- -t "rejects a viewer" # one test by name

# LocalStack-backed tiers (need Docker); both self-skip when their env vars are unset:
pnpm run localstack:up && pnpm run test:integration && pnpm run localstack:down  # Tier A: repo+services vs real DynamoDB
pnpm run test:e2e                                                                # Tier B: deploy stack + black-box HTTP

# Single dev loop: deploy into LocalStack + esbuild --watch hot reload; prints Function URLs + a fresh API key:
pnpm run localstack:up && cp .env.example .env && pnpm run dev

For how to write tests (the independent-oracle rule, the L0–L5 layers, fakes, property tests, determinism, coverage) read TESTING.md. Dev-loop / LocalStack details live in scripts/dev.mjs. Gotchas worth knowing up front:

  • The dev loop runs the real Lambda runtime (so the DynamoDB Streams → webhook path fires); the entrypoints are the Lambda handlers only — there is no local.ts, no :8000, no public ports (LocalStack + Function URLs are localhost-only; reach a remote box via SSH forwarding).
  • One shared LocalStack on :4566 serves every session; each working copy deploys its own dev stack, named from a persisted, gitignored .turjuman-dev marker. dev:teardown deletes just this copy's stack; localstack:down wipes the whole emulator and every session — never use it to clean up one session.

Read the full file on GitHub · 123 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. 8d ago First seen · 123 lines · 2,340 tokens per session scan A 4bc03dff9ad9

Subscribe to this mod's changes

turjuman CLAUDE.md is an instructions file published in the GitHub repository mogharsallah/turjuman (1 stars, last pushed 2mo ago), licensed MIT. It adds 2,340 tokens to every session, about $0.0117 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

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

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

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

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 · 7,104 tokens