Borrowing it
Nothing to install: this file belongs to notforyou23/home23. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/notforyou23/home23/main/CLAUDE.mdgit clone --depth 1 https://github.com/notforyou23/home23Wrote 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/notforyou23/home23/claude-md)<a href="https://agentmods.dev/instructions/notforyou23/home23/claude-md"><img src="https://agentmods.dev/badge/instructions/notforyou23/home23/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.
<a href="https://agentmods.dev/instructions/notforyou23/home23/claude-md"><img src="https://agentmods.dev/badge/instructions/notforyou23/home23/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01426 | $0.01426 |
| Opus 5.5 | $0.00570 | $0.00570 |
| Sonnet 5.5 | $0.00285 | $0.00285 |
| Haiku 4.5 | $0.00143 | $0.00143 |
Grade A, and why
home23 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 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.
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Current working instructions
Read AGENTS.md and docs/reference/DEVELOPMENT-WORKFLOW.md before work. They establish source ownership, concurrent-work handling and release boundaries. The developer reference below does not supersede them.
Upgrade/Host/embedding work follows docs/design/HOME-UPDATES-AND-PORTABILITY.md. Its continuity reset supersedes the old product-completion and embedder handoff sequences. Do not treat lifecycle adoption, software delivery and changing an existing encoder as one mandatory migration.
The lead owns review, relevant verification, local commits and integration. Worker restrictions do not remove those responsibilities or create new owner approval requirements. Follow the shared agreement's task record and completion rules, preserving the owner's explicit scope and authorization.
Home23 Developer Guide
Home23 is an installable AI operating system for persistent local agents. Keep the public repository portable and keep user-specific runtime state outside Git.
Quick Start
git clone https://github.com/notforyou23/home23.git
cd home23
node cli/home23.js setup
setup creates local config, opens the web-guided first-run page, and walks through providers, first personal agent, owner/user facts, purpose, starter ingestion folders, model choice, and launch.
For the older terminal-guided flow:
node cli/home23.js setup --cli
For automation or repeat agent creation, use the lower-level commands:
node cli/home23.js init
node cli/home23.js agent create <name>
node cli/home23.js start <name>
Repository Shape
src/- TypeScript harness, agent loop, tools, and scheduler.src/substrate/- Seed-owned surfaces (v2): turn expression, lived RECENT/NOW/facts/identity, the shared semantic matcher, perception-at-contact embedding.substrate/- the Seed itself (v2): hash-chained ledger, situation cells, metabolism, development rules (including sleep: consolidation + dream), membrane, growth, lobe recruitment, runner, journal, observatory. Seedocs/design/HOME23-V2-SUBSTRATE-DESIGN.md.engine/src/- engine, dashboard, cognition, memory, live-problem, and sensor modules.engine/src/substrate/- engine-side Seed readers (cognition grounding, dream day-residue).cli/- installer, PM2 management, agent creation, updates, and templates.- Cosmo is a standalone research application reached through its configured API; it is no longer a vendored
cosmo23/source tree. Readdocs/reference/COSMO-SEPARATION.mdfor ownership and cross-product test prerequisites. evobrew/- optional standalone application retained in source. Consumer Host packages omit it; Home23's chat/device/agency bridge remains insrc/routes/evobrew-bridge.ts, and saved home state is preserved.config/*.example- public config seeds.instances/- generated per-agent runtime state. Ignored by Git.
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 · +2 lines · +91 tokens per session c1f2aabb23f9
- 1mo ago Changed · +4 lines · +86 tokens per session 02ed767bce38
- 1mo ago Changed · +4 lines · +49 tokens per session 1022e4bc344e
- 2mo ago First seen · 116 lines · 1,200 tokens per session scan A 2db528b4fe6e
home23 CLAUDE.md is an instructions file published in the GitHub repository notforyou23/home23 (11 stars, last pushed yesterday), licensed MIT. It adds 1,426 tokens to every session, about $0.0057 per session on Opus 5.5. 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.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.