Norn: Instructions file for Claude Code

CLAUDE.md

Norn CLAUDE.md is an instructions file for Claude Code from samad001z/Norn. It costs 1,258 tokens per session, scanned A, original, MIT.

Project instructions for Norn, a local-first memory system for AI coding tools. It stores project context in local memory and provides a dashboard to view, search, edit, and delete it.

In plain words
What is it for?
Use it as build guidance for Norn’s TypeScript MCP server, local SQLite storage, memory operations, and Next.js dashboard.
Why use it?
It gives the project a fixed technical scope and design direction so development stays focused on transparent, user-controlled memory.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is samad001z/Norn's own configuration. It tells Claude Code how to work on Norn 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 Norn configures →

Reuse

Borrowing it

Nothing to install: this file belongs to samad001z/Norn. 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/samad001z/Norn/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/samad001z/Norn

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 Norn CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/samad001z/norn/claude-md.svg)](https://agentmods.dev/instructions/samad001z/norn/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/samad001z/norn/claude-md"><img src="https://agentmods.dev/badge/instructions/samad001z/norn/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,258 This file is loaded in full into every session.
When invoked 1,258 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 $0.01258 $0.01258
Opus 5 $0.00629 $0.00629
Sonnet 5 $0.00252 $0.00252
Haiku 4.5 $0.00126 $0.00126

Measured 7d ago against content hash 04755e265825, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

Norn 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 7d 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 · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Norn — Project Context

What this is

A local-first memory layer for AI coding tools. An MCP server that remembers context across sessions/projects, plus a dashboard to SEE, SEARCH, EDIT, DELETE every memory. The differentiator is transparency + control + craft — not the retrieval algorithm.

Stack (v1)

  • MCP server: TypeScript, @modelcontextprotocol/sdk
  • Store: local SQLite + sqlite-vec (local-first = privacy + zero infra). Supabase pgvector later, only when cloud sync is needed.
  • Embeddings: small embedding model (swappable behind an interface).
  • Dashboard: Next.js (App Router) + TypeScript + Tailwind + shadcn/ui + Framer Motion.

v1 scope — build ONLY this

  • MCP tools: remember(), recall(), forget(), list()
  • Dashboard: list memories, full-text + semantic search, inline edit, delete, per-project grouping.
  • One "wow": it just remembers, and you can see everything.

NOT in v1 (resist)

Teams, multi-user, auth beyond local, billing, voice, 10 framework integrations.

Design direction (do NOT use generic AI-slop looks)

  • Mood: premium, quiet, editorial. Think "the well of memory" — depth, calm, precision.
  • Spend boldness in ONE signature element; keep everything else disciplined and quiet.
  • Typography carries the personality: pick a characterful display face used sparingly + a clean body face + a mono/utility face for memory metadata. Set a real type scale.
  • Avoid the three AI defaults: cream+serif+terracotta; near-black+acid-green; broadsheet hairline columns. If you reach for one, justify it or change it.
  • Quality floor, non-negotiable: responsive to mobile, visible keyboard focus, prefers-reduced-motion respected.
  • Copy is design material: name things by what the user controls ("Forget this memory", not "Delete vector"). Active voice. Empty states invite action.

Working rules

  • Update this file when decisions change. Small commits. Ask before adding scope.

Repo layout (decided)

  • /core@samad001z/norn-core: Storage interface + SqliteStorage (SQLite + sqlite-vec), swappable Embedder interface. Shared by server and web.
  • /server@samad001z/norn-server: MCP server over stdio. Tools: remember(content, tags?, project?), recall(query, limit?), forget(id), list(project?).

Read the full file on GitHub · 77 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. 7d ago First seen · 77 lines · 1,258 tokens per session scan A 04755e265825

Subscribe to this mod's changes

Norn CLAUDE.md is an instructions file published in the GitHub repository samad001z/Norn (3 stars, last pushed 1mo ago), licensed MIT. It adds 1,258 tokens to every session, about $0.0063 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

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