houston: Instructions file for Claude Code

CLAUDE.md

houston CLAUDE.md is an instructions file for Claude Code from gethouston/houston. It costs 3,494 tokens per session, scanned A, original, MIT.

A set of project instructions for Houston, a TypeScript engine and host that powers desktop and cloud applications, including its repository layout and development loop.

In plain words
What is it for?
Use it when working on Houston’s runtime, host, shared client layer, migrations, protocol, or frontend, and when checking the development commands and known stale components.
Why use it?
It gives coding agents the project map and rules they need before changing code, reducing mistakes caused by outdated assumptions about where behavior lives.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

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

Reuse

Borrowing it

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

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 houston CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/gethouston/houston/claude-md.svg)](https://agentmods.dev/instructions/gethouston/houston/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/gethouston/houston/claude-md"><img src="https://agentmods.dev/badge/instructions/gethouston/houston/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,494 This file is loaded in full into every session.
When invoked 3,494 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 $0.03494 $0.03494
Opus 5 $0.01747 $0.01747
Sonnet 5 $0.00699 $0.00699
Haiku 4.5 $0.00349 $0.00349

Measured 4d ago against content hash 7ff00b5df780, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

houston 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 · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Houston

Houston is ONE TypeScript engine — the pi runtime (packages/runtime, the only agent loop) behind the host (packages/host) — serving desktop and cloud from the same code, with one shared client behavior layer (@houston/sdk) bound by every surface. The code is the truth: there is no separate knowledge base. Read the module and its tests before changing it; this file holds only the non-obvious map and the rules.

Repo map

Path What it is
app/src Shared React frontend. Runs verbatim as packages/web
app/src-tauri Tauri 2 shell: spawns the Bun-compiled host sidecar (binaries/houston-engine-<triple>). OS-native glue only, no domain logic
packages/runtime The pi engine. Single-workspace, tenancy-free. Providers are in-process (src/ai/providers.ts) — no provider CLIs
packages/host The host server (protocol v3). Same server for desktop and cloud, different adapter profiles. Boot migrations: src/migrate/
packages/domain / packages/protocol Domain logic (.houston layout, schemas, cron, portable) / v3 wire types + zod
packages/sdk Client behavior layer (turn lifecycle, conversation VM). Every surface binds it
packages/web Web build of app/src + Playwright e2e/visual suites (see packages/web/e2e/README.md)
ui/ @houston-ai/* React packages, props-only. @houston-ai/engine-client is the TS front door
packages/design-tokens Visual values. Tokens win over any hardcoded literal
mobile/ios Native SwiftUI app over @houston/sdk. Parity notes: mobile/PARITY*.md
agentstore/ Agent Store frontend (agents.gethouston.ai)
selfhost/ Docker + Caddy self-host image (selfhost/README.md)
skills/ Task procedures: /release, /debug, /build-app-local, /design-review, /frontend-design
docs/adr/ Architecture decision records
convergence/, store/ Historical: the Rust→TS cutover record; legacy bundled catalog data. Never the current map

Read the full file on GitHub · 134 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 Changed · +69 tokens per session 7ff00b5df780
  2. 7d ago First seen · 134 lines · 3,425 tokens per session scan A 6e9039f9d3e6

Subscribe to this mod's changes

houston CLAUDE.md is an instructions file published in the GitHub repository gethouston/houston (112 stars, last pushed today), licensed MIT. It adds 3,494 tokens to every session, about $0.0175 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

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

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

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

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

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

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