Borrowing it
Nothing to install: this file belongs to JuliusBrussee/cavemem. 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/JuliusBrussee/cavemem/main/CLAUDE.mdgit clone --depth 1 https://github.com/JuliusBrussee/cavememWrote 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/juliusbrussee/cavemem/claude-md)<a href="https://agentmods.dev/instructions/juliusbrussee/cavemem/claude-md"><img src="https://agentmods.dev/badge/instructions/juliusbrussee/cavemem/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/juliusbrussee/cavemem/claude-md"><img src="https://agentmods.dev/badge/instructions/juliusbrussee/cavemem/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 | $0.01990 | $0.01990 |
| Opus 5.5 | $0.00796 | $0.00796 |
| Sonnet 5.5 | $0.00398 | $0.00398 |
| Haiku 4.5 | $0.00199 | $0.00199 |
Grade A, and why
cavemem 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cavemem — Agent Playbook
This file is the source of truth for AI coding assistants working on this repository. Follow it before generating code, tests, or documentation. If a request conflicts with this file, pause and ask.
Project identity
cavemem is a cross-agent persistent memory system for coding assistants. It captures observations from editor sessions, compresses prose using the project's deterministic caveman grammar, stores entries in a local SQLite + vector index, and exposes them to agents through a Model Context Protocol (MCP) server and a local web viewer.
The signature property of the project is that memory is stored compressed. Every write path runs text through @cavemem/compress. Every human-facing read path runs it back through @cavemem/compress#expand. Model-facing reads may keep content compressed when the caller requests it.
Non-negotiable rules
- All persisted prose must pass through
packages/compressbefore hitting storage. Writing raw prose to SQLite is a defect. If you add a new write path, it must useMemoryStore, which enforces this. - Never compress technical tokens. Code blocks, inline code, URLs, file paths, shell commands, version numbers, dates, numeric literals, and quoted identifiers are preserved byte-for-byte. The tokenizer in
packages/compress/src/tokenize.tsis the single authority. - Round-trip tests must pass. Any change to the compressor, the lexicon, or the tokenizer requires
pnpm --filter @cavemem/compress testgreen, including the technical-token preservation suite. - Progressive disclosure in MCP.
searchandtimelinereturn compact results (IDs + snippets). Full observation bodies are only returned byget_observations(ids[]). Do not bloat the compact shapes. - Hot-path hooks are fast. Hook handlers in
packages/hooksmust complete under 150 ms p95. Summarization, embedding, and indexing are handed off to the worker. No network calls in hooks. - Privacy is enforced at the write boundary. Content inside
<private>…</private>tags is stripped. Paths matchingsettings.excludePatternsare never read. Neither appears in logs. - Local by default. Default embedding provider is local (Transformers.js). Remote providers are opt-in via settings. Do not add default network calls.
- No silent failures. Hook and worker errors are logged as structured JSON; user-visible commands surface failures with a non-zero exit code and a short message.
- No daemon on the write path. Hooks write observations synchronously through
MemoryStore.addObservation— never across a network or HTTP boundary. Hooks may detach-spawn the worker to kick off background embedding, but they must never wait on it. If the worker is down, writes still succeed; only the semantic-search side is degraded (BM25 keeps working).
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 First seen · 95 lines · 1,990 tokens per session scan A eb085fe4b66d
cavemem CLAUDE.md is an instructions file published in the GitHub repository JuliusBrussee/cavemem (676 stars, last pushed 2mo ago), licensed MIT. It adds 1,990 tokens to every session, about $0.0080 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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.