booksum: Instructions file for Claude Code

CLAUDE.md

booksum CLAUDE.md is an instructions file for Claude Code from dorianspitz23/booksum. It costs 1,953 tokens per session, scanned A, original, MIT.

Instructions for BookSum, a browser-based book summariser built with React and TypeScript that stores data locally and uses Google Gemini for summaries.

In plain words
What is it for?
Use them when changing BookSum's features, audit records, deployment workflow, storage, or AI integration.
Why use it?
They describe the finished project, its local-only storage and user-provided AI key, and rules for preserving important design decisions.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is dorianspitz23/booksum's own configuration. It tells Claude Code how to work on booksum 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 booksum configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dorianspitz23/booksum. 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/dorianspitz23/booksum/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/dorianspitz23/booksum

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 booksum CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dorianspitz23/booksum/claude-md/github.svg)](https://agentmods.dev/instructions/dorianspitz23/booksum/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/dorianspitz23/booksum/claude-md"><img src="https://agentmods.dev/badge/instructions/dorianspitz23/booksum/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 booksum CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/dorianspitz23/booksum/claude-md"><img src="https://agentmods.dev/badge/instructions/dorianspitz23/booksum/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,953 This file is loaded in full into every session.
When invoked 1,953 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 $0.01953 $0.01953
Opus 5 $0.00977 $0.00977
Sonnet 5 $0.00391 $0.00391
Haiku 4.5 $0.00195 $0.00195

Measured 10d ago against content hash f7ac1e820e51, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

booksum 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 10d 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 · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BookSum — Project Instructions

Local-first book summariser. React 19 + Vite 8 + TypeScript, IndexedDB for storage, Google Gemini for AI. No server, no accounts, no backend.

Current state

All four phases are complete: foundation, quality, features, and a defect sweep that worked an audit backlog of 441 findings through to zero by severity. The project is published under MIT at dorianspitz23/booksum.

There is no hosted demo, deliberately: the app asks each visitor for their own Gemini key, and hosting a page that collects keys is a decision rather than a default. deploy.yml can still publish one to GitHub Pages, but only when run by hand — do not make it automatic without asking.

  • audit-reports/_harvest/PROGRESS.md — what was done in each wave, and the traps hit along the way. Worth reading before a large change.
  • audit-reports/_harvest/live-findings.json and findings-session*.json — the findings themselves, each with a file, a line and a stated mechanism.
  • node audit-reports/_harvest/closed.mjs counts what is closed; open.mjs <severity> <n> lists what remains. A finding counts as closed only when its id is named in a commit message. If you reopen this workflow, keep naming ids or the counter drifts.
  • audit-reports/_harvest/FEATURE-REQUESTS.md — findings that were feature requests rather than defects. Deliberately not built. Do not implement these without asking.

History: docs/superpowers/specs/ holds the design; docs/superpowers/plans/ holds one plan per phase. Commit 670b5fe is the untouched Google AI Studio original, so any change is a diff against it.

The audit worktrees are dead — do not wait on them

git worktree list may show ~30 worktrees under .worktrees/ on audit/* and apply/* branches. None are running. They are frozen copies of the repo at older commits, kept only because four of them hold audit reports whose findings are already harvested into _harvest/live-findings.json. Do not go re-reading the worktrees for findings.

Read the full file on GitHub · 120 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. 10d ago First seen · 120 lines · 1,953 tokens per session scan A f7ac1e820e51

Subscribe to this mod's changes

booksum CLAUDE.md is an instructions file published in the GitHub repository dorianspitz23/booksum (11 stars, last pushed 2d ago), licensed MIT. It adds 1,953 tokens to every session, about $0.0098 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

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

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

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