Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/yanlinglabs/norma/claude-mdgit clone --depth 1 https://github.com/yanlingLabs/normaWrote 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/yanlinglabs/norma/claude-md)<a href="https://agentmods.dev/instructions/yanlinglabs/norma/claude-md"><img src="https://agentmods.dev/badge/instructions/yanlinglabs/norma/claude-md.svg" alt="Measured on agentmods" 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 | $0.03053 | $0.03053 |
| Opus 5 | $0.01527 | $0.01527 |
| Sonnet 5 | $0.00611 | $0.00611 |
| Haiku 4.5 | $0.00305 | $0.00305 |
Grade A, and why
norma 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 4d 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 — 117 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.
What this is
Norma is a macOS-native AI assistant: a TypeScript/Bun daemon (norma-core) that runs the agent loop, plus a native Swift menu-bar app that gives it a face. They talk JSON-RPC 2.0 over NDJSON on a Unix socket (~/.norma/run/core.sock). The daemon is the single source of truth; every client (CLI, app) is a view over its event stream.
Commands
bun install # install everything (bun is the runtime; pnpm workspaces orchestrate)
# Tests
pnpm test # all workspaces, serially
cd packages/core && bun test # one package
bun test path/to/file.test.ts # one file (path substring match)
bun test -t "test name" # one test by name
# Protocol codegen — REQUIRED after changing packages/protocol/src (events/methods)
pnpm protocol:generate # regenerates JSON schema + Swift round-trip fixtures
# Workflows e2e — proves the sandboxed runtime on the REAL compiled artifact (dist/norma-core)
bun run verify:workflow
# Swift
cd apple/NormaProtocol && swift test # protocol mirror round-trip tests
cd apple/NormaKit && swift test # daemon client library
cd apple/Norma && xcodegen generate && \
xcodebuild -project Norma.xcodeproj -scheme Norma -destination 'platform=macOS' build
# Run the daemon + CLI in dev
cd packages/cli
bun src/main.ts daemon run # headless daemon
bun src/main.ts -p "hello" # one-shot prompt (separate terminal)
bun src/main.ts # interactive TUI (Ink)
# Dev profile: the Debug app is "Norma Dev" (com.norma.app.dev) on ~/.norma-dev, keychain
# com.norma.core.dev; the global `norma-dev` command (installed by the dev app's menu) is an
# env-setting bun wrapper. The distribution app owns `norma` (symlink installed from the app /
# brew) on ~/.norma, keychain com.norma.core. Explicit NORMA_HOME always wins over both defaults.
# TWO TRAPS: (1) plain `norma` is the DIST CLI — with a dead socket it AUTO-LAUNCHES the dist app
# (`open -g -b com.norma.app`), so never use it for dev/test work: use `norma-dev`, or a temp
# NORMA_HOME with a manually-spawned `daemon run`. (2) Debug builds do NOT embed norma-core —
# "Norma Dev" cannot self-spawn a daemon; start the dev daemon below FIRST or the orb shows
# disconnected.
NORMA_HOME=~/.norma-dev NORMA_PROFILE=dev bun src/main.ts daemon run # dev daemon (or: norma-dev daemon run)
# Versioning — never edit versions by hand; VERSION file (#.#.### format) is canonical
bun run version:bump # +0.0.001 (also --minor / --major)
bun run version:sync # restamp package.jsons/plists from VERSION
# Release (one command → signed, notarized, stapled zip+DMG+appcast+cask+gh release)
bun run scripts/release.ts --dry-run --no-bump # full rehearsal, never publishes
bun run scripts/release.ts # real release (bumps version first)
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.
- 4d ago First seen · 117 lines · 3,053 tokens per session scan A 518dda1ca130
norma CLAUDE.md is an instructions file published in the GitHub repository yanlingLabs/norma (2 stars, last pushed 7d ago), licensed Apache-2.0. It adds 3,053 tokens to every session, about $0.0153 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.
Other instructions, from other repositories
LobsterAI AGENTS.md
AGENTS.md instructions for netease-youdao/LobsterAI, covering agents.md, instruction scope, project snapshot, cowork vs openclaw and commands.
warren AGENTS.md
AGENTS.md instructions for jayminwest/warren, covering agents.md, what this project is, runtime topology, the burrow absorption (plan pl-3007) and per-project config (.warren/config.yaml).
hivekeep CLAUDE.md
Claude Code instructions for MarlBurroW/hivekeep, covering hivekeep, documentation map, tech stack, key conventions and naming.
useagent CLAUDE.md
Claude Code instructions for useagenthq/useagent, covering useagent - claude.md and hard rules.
factory CLAUDE.md
Claude Code instructions for watt-mind/factory: Claude, please refer to AGENTS.md and docs/protocol.md for the primary repository context, architecture, commands, operational rules, and tracker issue management standards.
factory GEMINI.md
Gemini CLI instructions for watt-mind/factory: Gemini, please refer to AGENTS.md and docs/protocol.md for the primary repository context, architecture, commands, operational rules, and tracker issue management standards.