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.
npx agentmods add instructions/uu201/character-arc/claude-mdgit clone --depth 1 https://github.com/uu201/character-arcWrote 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.
[](https://agentmods.dev/instructions/uu201/character-arc/claude-md)<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>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.
| Model | Per session | Once 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 |
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.
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/Oelectron/preload/— context-bridge surface exposed aswindow.characterArcelectron/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:
- App boot (
renderer/src/main.ts) creates Pinia, callsuseAppStore().initialize(), which IPC-loads the workspace snapshot from SQLite, thenapp.mount('#app'). - Edits mutate the Pinia store (
renderer/src/stores/app.ts); a debounced persistence layer (renderer/src/features/workspace/persistence.ts) writes back viawindow.characterArc.saveWorkspace/saveAppSettings. - Main holds
latestWorkspaceSnapshotin memory for AI tasks to read; onbefore-quitit flushes one last time. - The renderer-side
characterArcAPI and the main-side IPC channels share names likecharacterarc:*.IPC_CHANNELSinelectron/shared/ipc-types.tsis partial — most channel names are still string literals on both sides.
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.
- 4d ago First seen · 97 lines · 2,231 tokens per session scan A b660f2a3486f
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.
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.
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.
nanobrowser CLAUDE.md
Instructions for nanobrowser/nanobrowser, covering claude.md, project overview, development commands, workspace tips and architecture.
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).
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).
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.