Cabinet is a self-hosted knowledge base and startup workspace that stores files, AI workspaces, and agent memory as Markdown files on disk. It is designed for people who want an AI team and their data kept on their own machine without a database or vendor lock-in. Its catalogue instruction supports the workflow for using Cabinet.
Borrowing it
Nothing to install: this file belongs to cabinetai/cabinet. 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/cabinetai/cabinet/main/CLAUDE.mdgit clone --depth 1 https://github.com/cabinetai/cabinetWrote 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/cabinetai/cabinet/claude-md)<a href="https://agentmods.dev/instructions/cabinetai/cabinet/claude-md"><img src="https://agentmods.dev/badge/instructions/cabinetai/cabinet/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/cabinetai/cabinet/claude-md"><img src="https://agentmods.dev/badge/instructions/cabinetai/cabinet/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 | $0.00215 | $0.00215 |
| Opus 5.5 | $0.00086 | $0.00086 |
| Sonnet 5.5 | $0.00043 | $0.00043 |
| Haiku 4.5 | $0.00021 | $0.00021 |
Grade A, and why
cabinet 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 2mo 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.
What it actually says
CLAUDE.md
Cabinet is a self-hosted, AI-first knowledge base and "startup OS". Knowledge-base content lives as markdown files on disk; AI agents (backed by local CLI providers) read and write those files on schedules or on demand. Humans define intent, agents do the work
docs/CLAUDE.md holds a longer, feature-by-feature ruleset (skills, knowledge sources, registry,
editor). Read it when you touch those subsystems. This file covers the parts you need for almost any
task.
Three processes and a data directory. Understanding the split is most of the battle.
**1. Next.js app **2. Daemon **3. Electron shell
PROGRESS.md
After every change to this project, append an entry to PROGRESS.md:
[YYYY-MM-DD] Brief description of what changed.
This is mandatory and is the project's running changelog. Existing entries are detailed (what changed, why, what was verified) — match that.
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.
- 2mo ago First seen · 27 lines · 215 tokens per session scan A dc102c631ebe
cabinet CLAUDE.md is an instructions file published in the GitHub repository cabinetai/cabinet (2,892 stars, last pushed 2mo ago), licensed MIT. It adds 215 tokens to every session, about $0.0009 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.
cabinet CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cabinet CLAUDE.mdcabinetai/cabinet | Instructions file | 2.9k | 2mo ago | MIT | A | 215 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | 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 | 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 |