What is Sonder_Engine CLAUDE.md?

A set of instructions for AI assistants working on Sonder Engine, with links to its project workflow, architecture, database, testing, and design documents. It identifies which documents are the source of truth for different changes.

Use it at the start of non-trivial work to choose the correct guide, update generated maps properly, follow database change checks, and keep design status accurate.

It directs the assistant to the relevant project rules before making changes, lowering the risk of violating database, testing, documentation, or architecture requirements.

How N0819/Sonder_Engine configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to N0819/Sonder_Engine. 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/N0819/Sonder_Engine/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/N0819/Sonder_Engine

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/n0819/sonder_engine/claude-md/github.svg)](https://agentmods.dev/instructions/n0819/sonder_engine/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/n0819/sonder_engine/claude-md"><img src="https://agentmods.dev/badge/instructions/n0819/sonder_engine/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/n0819/sonder_engine/claude-md"><img src="https://agentmods.dev/badge/instructions/n0819/sonder_engine/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 7,395 This file is loaded in full into every session.

When invoked 7,395 The same file — it is already loaded in full.

Security scan A 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.07395	$0.07395
Opus 5.5	$0.02958	$0.02958
Sonnet 5.5	$0.01479	$0.01479
Haiku 4.5	$0.00739	$0.00739

Measured 1mo ago against content hash 4c26c082bc6f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Sonder_Engine CLAUDE.md scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

4. [`docs/guides/DATABASE.md`](docs/guides/DATABASE.md) — schema, write helpers (`q`/`qi`/`qtx`/`transaction`/`wget`/`wset`), and the schema-change checklist.

CLAUDE.md · 292 lines

How it starts

The opening of the file, as written. The whole thing — 292 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.

Start here

This repo already maintains detailed docs for coding agents. Read them before making non-trivial changes:

AGENTS.md — edit routing table (which files to touch for which change), core invariants, source-of-truth order, and safe change workflow. Read this first for any behavioral change.
docs/guides/PIPELINE.md — exact opening-turn and normal-turn execution flow, stage-by-stage.
docs/CODE_MAP.md — generated index of modules, functions, routes, DB tables, and frontend sections. Regenerate with make map; do not hand-edit.
docs/guides/DATABASE.md — schema, write helpers (q/qi/qtx/transaction/wget/wset), and the schema-change checklist.
docs/guides/TESTING.md — fast/full/browser tiers, dependency constraints, and CI policy.
Design.md — product philosophy, architecture, a verified conformance table (built / partial / not built), and structural debt. Its status rows were checked against source; keep them that way by editing the row in the same commit as the behaviour.
docs/UNBUILT.md — the register of unfinished work: known defects, the roadmap, deferred audit findings, and every design-note residual. It is meant to be the only status list and is not: Design.md's conformance table, each design note's Status: header, docs/guides/FEATURES.md's (partial) markers and docs/design/OFFSCREEN_WORLD_COMPLETION.md's per-item tags are four more. When they disagree, fix UNBUILT.md first. Delete an entry in the commit that lands it; add the corresponding row to Design.md.
docs/README.md — the documentation index. docs/guides/ is authority, docs/design/ is argument, docs/experiments/ is evidence, docs/archive/ is superseded.
agents/README.md — how to add a new pipeline stage.

Read the full file on GitHub · 292 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 · +288 tokens per session 4c26c082bc6f
2mo ago Changed · +69 lines · +1,172 tokens per session bbba5773accb
2mo ago First seen · 223 lines · 5,935 tokens per session scan A a1a44603be67

Subscribe to this mod's changes

Sonder_Engine CLAUDE.md is an instructions file published in the GitHub repository N0819/Sonder_Engine (60 stars, last pushed 6d ago), licensed MIT. It adds 7,395 tokens to every session, about $0.0296 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Sonder_Engine CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Sonder_Engine CLAUDE.mdN0819/Sonder_Engine	Instructions file	60	6d ago	MIT	A	7,395	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

Sonder_Engine: Instructions file for Claude Code