character-arc CLAUDE.md

character-arc CLAUDE.md is an instructions file for coding agents from uu201/character-arc. It costs 2,231 tokens per session, scanned A, original, MIT.

Repository instructions for CharacterArc, an Electron desktop app for novel writing. They describe its commands, three-part architecture, data flow, and SQLite workspace store.

In plain words
What is it for?
Use them when installing dependencies, running or building the app, changing its Vue interface, Electron processes, AI pipeline, or SQLite data handling.
Why use it?
They explain how the app is organised and which build check to run, reducing guesswork when making changes.

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/uu201/character-arc/claude-md
Clone the repo
git clone --depth 1 https://github.com/uu201/character-arc

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 character-arc CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/uu201/character-arc/claude-md.svg)](https://agentmods.dev/instructions/uu201/character-arc/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/uu201/character-arc/claude-md"><img src="https://agentmods.dev/badge/instructions/uu201/character-arc/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,231 This file is loaded in full into every session.
When invoked 2,231 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 $0.02231 $0.02231
Opus 5 $0.01115 $0.01115
Sonnet 5 $0.00446 $0.00446
Haiku 4.5 $0.00223 $0.00223

Measured 4d ago against content hash b660f2a3486f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

character-arc 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 4d 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 · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Commands

Package manager: pnpm (pinned to 10.33.2 in package.json). Scripts shell out via Windows set syntax — on macOS/Linux replace set ELECTRON_RUN_AS_NODE=&& with cross-env ELECTRON_RUN_AS_NODE= or strip the prefix.

pnpm install          # install deps (uses npmmirror via .npmrc)
pnpm run dev          # electron-vite dev: starts main + preload + renderer (Vite on 127.0.0.1, port auto-selected)
pnpm run build        # vue-tsc --noEmit (full type check) then electron-vite build
pnpm run preview      # run the production build locally
pnpm run dist         # type check + build + electron-builder (Windows NSIS installer)

There is no test runner, linter, or formatter configured. "Build = type check" — vue-tsc --noEmit is the only static gate, and pnpm run build will fail loudly on TS errors. Run it before declaring work done.

Architecture

CharacterArc is an Electron 37 + Vue 3.5 + TypeScript desktop app for novel writing. Three processes, three roots:

  • electron/main/ — Node main process: SQLite, AI pipeline, IPC handlers, file I/O
  • electron/preload/ — context-bridge surface exposed as window.characterArc
  • electron/shared/ — types shared across process boundaries (@shared/* alias)
  • renderer/src/ — Vue 3 + Pinia + Naive UI + TipTap (@/* alias → renderer/src/*)

Build outputs land in dist-electron/{main,preload} and out/renderer. Entry is dist-electron/main/index.js (see package.json#main).

Data flow

The renderer never touches the filesystem or AI providers directly. Everything goes through IPC:

  1. App boot (renderer/src/main.ts) creates Pinia, calls useAppStore().initialize(), which IPC-loads the workspace snapshot from SQLite, then app.mount('#app').
  2. Edits mutate the Pinia store (renderer/src/stores/app.ts); a debounced persistence layer (renderer/src/features/workspace/persistence.ts) writes back via window.characterArc.saveWorkspace / saveAppSettings.
  3. Main holds latestWorkspaceSnapshot in memory for AI tasks to read; on before-quit it flushes one last time.
  4. The renderer-side characterArc API and the main-side IPC channels share names like characterarc:*. IPC_CHANNELS in electron/shared/ipc-types.ts is partial — most channel names are still string literals on both sides.

Read the full file on GitHub · 97 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. 4d ago First seen · 97 lines · 2,231 tokens per session scan A b660f2a3486f

Subscribe to this mod's changes

character-arc CLAUDE.md is an instructions file published in the GitHub repository uu201/character-arc (543 stars, last pushed 3d ago), licensed MIT. It adds 2,231 tokens to every session, about $0.0112 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

pioneer AGENTS.md

AGENTS.md instructions for pioneerdotai/pioneer, covering database architecture, runtime model, scheduling classes, never hold database capacity during other work and transactions and batches.

pioneerdotai/pioneer · 1,291 tokens

mcp-toolbox GEMINI.md

Gemini CLI instructions for googleapis/mcp-toolbox, covering mcp toolbox context & style guide, project overview, tech stack, key directories and development workflow.

googleapis/mcp-toolbox · 3,611 tokens

nanobrowser CLAUDE.md

Instructions for nanobrowser/nanobrowser, covering claude.md, project overview, development commands, workspace tips and architecture.

nanobrowser/nanobrowser · 2,693 tokens

bifrost AGENTS.md

Instructions for bifrost-proxy/bifrost, covering bifrost 项目开发规则, 执行心法, 执行模式与完成定义, 任务模式判定 and 变更类型与验证路由(先判定,后执行).

bifrost-proxy/bifrost · 16,937 tokens

Commonly-used-high-value-skills AGENTS.md

AGENTS.md instructions for seaworld008/Commonly-used-high-value-skills, covering repository agent instructions, architecture overview, installation root by client, golden rules and automated operations (sop for ai agents).

seaworld008/Commonly-used-high-value-skills · 4,045 tokens

memory-bridge AGENTS.md

AGENTS.md instructions for jiabaobei/memory-bridge, covering agents.md — 记忆桥项目规约(ai 协作会话必读), 版本与发布(硬性规则,所有者 2026-08-29 定), 架构铁律 and 工程习惯.

jiabaobei/memory-bridge · 421 tokens