smart-citizen CLAUDE.md

smart-citizen CLAUDE.md is an instructions file for coding agents from Osiris-DevWorks/smart-citizen. It costs 7,882 tokens per session, scanned A, original, Apache-2.0.

A set of instructions for working on Smart Citizen, a Windows app for editing Star Citizen game-localization text, using Claude Code.

In plain words
What is it for?
Use it when editing the app's source, scripts, or tests, especially when working with localization files, backups, or per-directory instructions.
Why use it?
It explains the project structure, writing style, and required directory guides so changes follow the repository's rules.

Instructions file

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 instructions/osiris-devworks/smart-citizen/claude-md
Clone the repo
git clone --depth 1 https://github.com/Osiris-DevWorks/smart-citizen

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 smart-citizen CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/osiris-devworks/smart-citizen/claude-md.svg)](https://agentmods.dev/instructions/osiris-devworks/smart-citizen/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/osiris-devworks/smart-citizen/claude-md"><img src="https://agentmods.dev/badge/instructions/osiris-devworks/smart-citizen/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 7,882 This file is loaded in full into every session.
When invoked 7,882 The same file — it is already loaded in full.
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 $0.07882 $0.07882
Opus 5 $0.03941 $0.03941
Sonnet 5 $0.01576 $0.01576
Haiku 4.5 $0.00788 $0.00788

Measured 3d ago against content hash ac428d6db5fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

smart-citizen 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 3d 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 · 278 lines

How it starts

The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file guides Claude Code (claude.ai/code) when working in this repo.

Before editing files under src/<dir>/, scripts/, or tests/, read that directory's CLAUDE.md first. See Per-directory guides below for the list.

Communication style

  • Plain words, short sentences. Cut adjectives, hedges, and throat-clearing. If a sentence isn't earning its weight, drop it.
  • One concept per message. When the work involves several distinct concepts, present the first, stop, and ask the user before moving on. Do not stack ideas, decisions, or trade-offs in a wall of text.
  • Prompt at decision points. When the next step needs the user's preference, judgment, or clarification, ask before proceeding. A one-line confirmation is cheaper than redoing work.

Project Overview

Smart Citizen (formerly SC Localization Editor) is a Windows-only PyQt6 GUI for customizing Star Citizen localization strings. Tagline: Smarter Strings for Star Citizen. Users edit strings in a table backed by the global source (locally cached base.ini from Data.p4k) merged with per-channel user.ini overrides, then apply the result to their game with backup management.

Branding: User-facing strings, registry path (Osiris DevWorks\Smart Citizen), and the default data root (Documents\Smart Citizen\) use the new name. AppSettings keeps one-shot migrators for the legacy Osiris DevWorks\SC Localization Editor registry tree and Documents\SC Localization Editor\ folder (rebrand was 0.9.0); keep them while pre-0.9 users may upgrade.

Version: VERSION.TXT is the sole source of truth. Now 2.3.1.

Build modes are covered in src/utils/CLAUDE.md under Portable vs registry build mode.

Per-directory guides

Directory-specific docs (read the one for the layer you're touching):

  • src/gui/CLAUDE.md — GUI layer (PyQt6 widgets, workers, table model).
  • src/utils/CLAUDE.md — settings, build-mode flag, P4K extraction, enhancement helpers.
  • src/parser/CLAUDE.md — INI parsing, status classification.
  • src/merger/CLAUDE.md — source merge engine.
  • src/models/CLAUDE.md — domain data models.
  • scripts/CLAUDE.md — standalone CLI scripts and the build pipeline.
  • tests/CLAUDE.md — test suite layout, pytest config.

Read the full file on GitHub · 278 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. 3d ago First seen · 278 lines · 7,882 tokens per session scan A ac428d6db5fc

Subscribe to this mod's changes

smart-citizen CLAUDE.md is an instructions file published in the GitHub repository Osiris-DevWorks/smart-citizen (99 stars, last pushed 5d ago), licensed Apache-2.0. It adds 7,882 tokens to every session, about $0.0394 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 2026-08-30.

Related

Other instructions, from other repositories

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

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

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 · 5,182 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 · 4,345 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

next.js 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