What is bartleby AGENTS.md?

A set of repository-specific instructions for working on the Bartleby codebase. It explains which documents to read, how its document database and command-line tools fit together, and what changes are allowed.

Use it when changing Bartleby, especially for structural edits, database schema changes, ingestion, or work that must follow the repository's contribution rules.

It gives a coding agent the project's rules and background before it edits code. This reduces changes that conflict with the architecture, database upgrade policy, or team workflow.

How jswest/bartleby configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to jswest/bartleby. 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/jswest/bartleby/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/jswest/bartleby

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/jswest/bartleby/agents-md/github.svg)](https://agentmods.dev/instructions/jswest/bartleby/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/jswest/bartleby/agents-md"><img src="https://agentmods.dev/badge/instructions/jswest/bartleby/agents-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/jswest/bartleby/agents-md"><img src="https://agentmods.dev/badge/instructions/jswest/bartleby/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,045 This file is loaded in full into every session.

When invoked 1,045 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 97% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5.1	$0.01045	$0.01045
Opus 5.5	$0.00418	$0.00418
Sonnet 5.5	$0.00209	$0.00209
Haiku 4.5	$0.00104	$0.00104

Measured 1mo ago against content hash b105f9072f85, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

bartleby AGENTS.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 1mo 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.

Origin

This is a copy

97% identical to bartleby CLAUDE.md — 63 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

AGENTS.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.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 · 62 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.

1mo ago Changed · +1 lines · +37 tokens per session b105f9072f85
1mo ago First seen · 61 lines · 1,008 tokens per session scan A cbb1e82a8a7b

Subscribe to this mod's changes

bartleby AGENTS.md is an instructions file published in the GitHub repository jswest/bartleby (12 stars, last pushed 1mo ago), licensed MIT. It adds 1,045 tokens to every session, about $0.0042 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 97% identical to bartleby CLAUDE.md, differing in 63 lines, and is treated as a copy.

Planning

bartleby AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
bartleby AGENTS.mdjswest/bartleby	Instructions file	12	1mo ago	MIT	A	1,045	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

bartleby: Instructions file for Codex