What is locus CLAUDE.md?

A set of project instructions for Claude Code, stored in a file named CLAUDE.md. It describes Locus, a markdown-based memory system where directories act as knowledge areas that an AI agent can consult when needed.

Use it when working on Locus or a similar agent memory system, especially when studying existing memory files, skills, commands, and project architecture.

The instructions give an agent the project’s purpose, memory conventions, and runtime structure before it changes the code. They also require the system to work with different AI agents, not only Claude.

How Nano-Nimbus/locus configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Nano-Nimbus/locus. 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/Nano-Nimbus/locus/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Nano-Nimbus/locus

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/nano-nimbus/locus/claude-md.svg)](https://agentmods.dev/instructions/nano-nimbus/locus/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/nano-nimbus/locus/claude-md"><img src="https://agentmods.dev/badge/instructions/nano-nimbus/locus/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 947 This file is loaded in full into every session.

When invoked 947 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.

Model	Per session	Once invoked
Fable 5.1	$0.00947	$0.00947
Opus 5	$0.00474	$0.00474
Sonnet 5	$0.00189	$0.00189
Haiku 4.5	$0.00095	$0.00095

Measured 7d ago against content hash 81f5817c305b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

locus 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 · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 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.

Project Purpose

Locus is a hierarchical markdown-based memory system for AI agents — each directory is a "room" (locus) in the palace, containing specific knowledge navigated on demand. Keeps context windows small while enabling precise, deep recall. Named for the atomic unit of the Method of Loci.

Must be agent-agnostic: usable by Claude, Codex, Gemini, or any LLM-based agent.

Existing Memory Patterns to Study

Before writing anything new, read these reference implementations:

Location	What it shows
`~/.claude/projects/<project>/memory/`	8-file memory system: MEMORY.md + specialty files
`~/.claude/projects/<project>/memory/`	Multi-agent orchestration memory
`~/.claude/skills/*/SKILL.md`	Skill definition format (9 skills to study)
`~/.claude/commands/`	Command format for reusable workflows

A mature memory directory typically has a ~200-line MEMORY.md plus specialty files for gotchas, deployments, and platform services.

Memory File Conventions (from existing projects)

Structure of MEMORY.md:

Project overview (1–3 sentences + key stats)
Architecture/topology
Configuration sections by subsystem
Key file paths
Current phase/status
References to specialty files

Specialty file patterns:

technical-gotchas.md — header-per-issue, symptom → root cause → resolution
platform-services.md — quick-reference table (service → version → IP/config)
deployment-issues.md — numbered issues with detailed logging

Context window discipline: MEMORY.md is always loaded (~200 line limit enforced by auto-memory system). Specialty files are read on demand. This is the core design constraint the skill must encode.

Runtime Architecture

Locus has two complementary interfaces:

1. SKILL.md files — the primary interface. Skills live in ~/.claude/skills/<name>/SKILL.md and are compatible with both Claude Code CLI and the Claude Agent SDK (settingSources: ["user", "project"]). The existing 9 skills are references: guided-walkthrough, project-triage, knowledge-capture, etc.

Read the full file on GitHub · 92 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.

7d ago First seen · 92 lines · 947 tokens per session scan A 81f5817c305b

Subscribe to this mod's changes

locus CLAUDE.md is an instructions file published in the GitHub repository Nano-Nimbus/locus (0 stars, last pushed 5mo ago), licensed MIT. It adds 947 tokens to every session, about $0.0047 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.

Memory and context

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

locus: Instructions file for Claude Code