bartleby CLAUDE.md

bartleby CLAUDE.md is an instructions file for coding agents from jswest/bartleby. It costs 1,009 tokens per session, scanned A, original, MIT.

A repository guide for Claude that explains the project’s structure, rules, and development workflow. It also documents a document-search system built on project-specific databases.

In plain words
What is it for?
Use it when changing the project’s architecture, database schema, document-ingestion code, command-line tools, or agent scripts.
Why use it?
It gives an AI agent the background and rules needed to make safe, consistent changes without guessing how the repository works.

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/jswest/bartleby/claude-md
Clone the repo
git clone --depth 1 https://github.com/jswest/bartleby

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 bartleby CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jswest/bartleby/claude-md.svg)](https://agentmods.dev/instructions/jswest/bartleby/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jswest/bartleby/claude-md"><img src="https://agentmods.dev/badge/instructions/jswest/bartleby/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,009 This file is loaded in full into every session.
When invoked 1,009 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 $0.01009 $0.01009
Opus 5 $0.00504 $0.00504
Sonnet 5 $0.00202 $0.00202
Haiku 4.5 $0.00101 $0.00101

Measured 4d ago against content hash cbd82e8fc70b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bartleby 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 · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Instructions for Claude working in this repo. Terse on purpose. Two companions:

  • ARCHITECTURE.md — load-bearing invariants and current state. Read it before changing anything structural. The decision log (the why behind past calls) now lives one-per-file under docs/decisions/.
  • CONTRIBUTING.md — the human narrative of the workflow below.

Bartleby ingests documents into per-project SQLite (FTS5 + sqlite-vec), then a skill scripts an agent over that DB. Two surfaces, one DB: the bartleby CLI (ingestion + helpers) and the skill scripts in bartleby/skill_scripts/.

Working agreements

  • No backwards compatibility, by default. Delete old code — no compat shims, no feature-flagged old paths, nothing left dormant. The one sanctioned exception: additive-only schema upgrades (new tables, indexes, nullable columns) get a _upgrade_vN_to_vN+1 entry in bartleby/db/upgrades.py so existing corpora run bartleby project upgrade <name> instead of re-ingesting.
  • Schema bumps mean re-ingest. A non-additive schema change bumps SCHEMA_VERSION in bartleby/db/schema.py and tells users to re-ingest. There is no automatic migration for those; don't write one. A bump that's additive in DDL but needs data populated at ingest is effectively non-additive — re-ingest-only.
  • Polymorphic chunks discipline. All writes to the chunks table go through the typed helpers in bartleby.db.chunks. Never INSERT into chunks directly — the CHECK (source_kind IN ...) constraint and the typed helpers are both load-bearing.
  • Memory enforcement is at script level, not prompt level. If a session has memory_enabled=0, search excludes prior-session findings regardless of flags or prompting. Don't soften this.
  • Skill scripts speak JSON. Print results as JSON to stdout; exit non-zero on error with {"error": ..., "code": ...}. Prose and progress go to stderr only.
  • When unsure, stop and ask. Most choices here have a prior conversation behind them. If something is ambiguous or uncovered, ask rather than wing it.
  • Smallest fix that fits. Prefer the simplest change that satisfies the requirement; don't add abstractions, flags, or migrations unless asked.

Read the full file on GitHub · 61 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 · 61 lines · 1,009 tokens per session scan A cbd82e8fc70b

Subscribe to this mod's changes

bartleby CLAUDE.md is an instructions file published in the GitHub repository jswest/bartleby (11 stars, last pushed 2d ago), licensed MIT. It adds 1,009 tokens to every session, about $0.0050 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