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/n0819/sonder_engine/claude-mdgit clone --depth 1 https://github.com/N0819/Sonder_EngineWrote 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/n0819/sonder_engine/claude-md)<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="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 | $0.07107 | $0.07107 |
| Opus 5 | $0.03553 | $0.03553 |
| Sonnet 5 | $0.01421 | $0.01421 |
| Haiku 4.5 | $0.00711 | $0.00711 |
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 today.
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. 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 withmake 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'sStatus:header,docs/guides/FEATURES.md's(partial)markers anddocs/design/OFFSCREEN_WORLD_COMPLETION.md's per-item tags are four more. When they disagree, fixUNBUILT.mdfirst. Delete an entry in the commit that lands it; add the corresponding row toDesign.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.
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.
- today Changed · +69 lines · +1,172 tokens per session bbba5773accb
- 4d ago First seen · 223 lines · 5,935 tokens per session scan A a1a44603be67
Sonder_Engine CLAUDE.md is an instructions file published in the GitHub repository N0819/Sonder_Engine (57 stars, last pushed 2d ago), licensed MIT. It adds 7,107 tokens to every session, about $0.0355 per session on Opus 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.
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).
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.
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.
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.
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).
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.