frozo-vault-mem: Instructions file for Claude Code

CLAUDE.md

frozo-vault-mem CLAUDE.md is an instructions file for Claude Code from frozo-ai/frozo-vault-mem. It costs 4,809 tokens per session, scanned A, original, MIT.

Repository instructions for vault-mem, an open-source local-first memory system built from a Markdown memory layer, an MCP server, a keeper, and a skills-file exporter.

In plain words
What is it for?
Planning or implementing changes in the vault-mem repository while following its current product plan and boundaries.
Why use it?
They define which project documents and architecture decisions guide changes, and separate this open-source code from the company's cloud product.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is frozo-ai/frozo-vault-mem's own configuration. It tells Claude Code how to work on frozo-vault-mem 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 frozo-vault-mem configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/ashishdhiman/WORK/Frozo-projects/frozo-vault-cloud.

Reuse

Borrowing it

Nothing to install: this file belongs to frozo-ai/frozo-vault-mem. 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/frozo-ai/frozo-vault-mem/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/frozo-ai/frozo-vault-mem

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 frozo-vault-mem CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/frozo-ai/frozo-vault-mem/claude-md/github.svg)](https://agentmods.dev/instructions/frozo-ai/frozo-vault-mem/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/frozo-ai/frozo-vault-mem/claude-md"><img src="https://agentmods.dev/badge/instructions/frozo-ai/frozo-vault-mem/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.

agentmods 80×15 button for frozo-vault-mem CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/frozo-ai/frozo-vault-mem/claude-md"><img src="https://agentmods.dev/badge/instructions/frozo-ai/frozo-vault-mem/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,809 This file is loaded in full into every session.
When invoked 4,809 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 $0.04809 $0.04809
Opus 5 $0.02405 $0.02405
Sonnet 5 $0.00962 $0.00962
Haiku 4.5 $0.00481 $0.00481

Measured 9d ago against content hash 627fd484da20, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

frozo-vault-mem 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 9d 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 · 209 lines

How it starts

The opening of the file, as written. The whole thing — 209 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.

Plan of record

The vault-mem-PRD.md at the repo root (v1.0, dated 2026-05-13) is the contract. It supersedes the personal-use PRD at docs/origin/personal-use-prd.md, which is retained for historical context only.

Vault-mem is a two-product play:

  • Vault-mem (OSS, MIT) — this repo. Local-first markdown memory layer + MCP server + keeper + skills-file exporter. Public at github.com/frozo-ai/frozo-vault-mem (note: PRD §11 wrote github.com/ashishdhiman/vault-mem — actual landing was under the frozo-ai org).
  • Vault Cloud (proprietary) — separate repo at /Users/ashishdhiman/WORK/Frozo-projects/frozo-vault-cloud. Multi-tenant Postgres on Supabase, connectors (Slack/GitHub/Linear/Notion/meetings), Next.js web UI, audit log. Cloud-specific code never lands here.

Vault-mem is the lead bet (Risk #7, decided 2026-05-13). Frozo and kincare are at maintenance until YC S26 application submits (deadline 2026-09-30). If asked to add scope here that pulls effort away from remaining PRD §11 milestones, flag it.

Repository state

  • Current branch: main. Recent feature branches (feat/phase-5-llm, feat/eval-harness, feat/skill-exporter, feat/supersede) are all merged.
  • Repo is PUBLIC on GitHub (frozo-ai/frozo-vault-mem, MIT, since 2026-04-28). Backups via git push — public remote is now the canonical mirror.
  • Production user: Ashish, generating ~5–15 memories/day across kincare, vault-mem, frozo, vault-cloud projects. Keeper runs via launchd every 30 min. Don't break the running keeper — this dogfood path is the YC demo.

PRD §11 roadmap status (timeline anchored to 2026-05-13 PRD approval):

Week Deliverable Status
0 PRD approved, decisions logged
1–2 Multi-tenant Postgres rewrite (Supabase, RLS, SSO) ✅ in vault-cloud
3 OSS repo public, MIT, landing page ✅ public; landing page status — verify
3–4 Slack connector + Haiku classifier + inbox→memory UX ✅ verified end-to-end 2026-05-19
5 Skills-file exporter (vault-mem export-skill) ✅ supports claude / cursor / windsurf / generic
6–7 Web UI v1 (Next.js + shadcn/ui): list, detail, search, manual write, connector config ✅ in vault-cloud/packages/web
8 Eval harness CLI + gold-set scaffolding ✅ code; gold sets scaffolded at vault-template/evals/ (3 design-partner sets — verify seeded)
8–9 GitHub + Linear connectors GitHub ✅ verified end-to-end 2026-05-19. Linear ✅ code exists, not yet verified live.
9–10 3 design partners fully onboarded ⏳ founder work — no code signal
11 memory_supersede MCP tool + conflict-detection primitives ✅ tool + CLI variant. Conflict-resolution UI lives in vault-cloud — verify
12 YC S26 application + 1-min video demo ⏳ founder work
+30 days Public Vault Cloud launch
+60 days Notion + meeting connectors GA Notion + meeting code exists in vault-cloud; GA = ⏳
+90 days First paid customer renewal

Read the full file on GitHub · 209 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. 9d ago First seen · 209 lines · 4,809 tokens per session scan A 627fd484da20

Subscribe to this mod's changes

frozo-vault-mem CLAUDE.md is an instructions file published in the GitHub repository frozo-ai/frozo-vault-mem (4 stars, last pushed 1mo ago), licensed MIT. It adds 4,809 tokens to every session, about $0.0240 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 2026-08-31.

Related

Other instructions, from other repositories

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

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 · 5,153 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

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

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

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.

deepseek-ai/deepseek-harness · 3,735 tokens