clauder CLAUDE.md

clauder CLAUDE.md is an instructions file for coding agents from MaorBril/clauder. It costs 757 tokens per session, scanned A, original, MIT.

Project instructions for Clauder, a persistent-memory service for Claude Code sessions. Persistent memory lets an agent save and retrieve facts, decisions, preferences, and messages between sessions.

In plain words
What is it for?
Use them when working in the Clauder project and when managing stored context, including remembering, recalling, forgetting, or exchanging messages with other sessions.
Why use it?
They make the agent load relevant previous context at the start of each session. This helps it continue work without losing earlier decisions or user preferences.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/maorbril/clauder/claude-md
Clone the repo
git clone --depth 1 https://github.com/MaorBril/clauder

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 clauder CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/maorbril/clauder/claude-md.svg)](https://agentmods.dev/instructions/maorbril/clauder/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/maorbril/clauder/claude-md"><img src="https://agentmods.dev/badge/instructions/maorbril/clauder/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 757 This file is loaded in full into every session.
When invoked 757 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00757 $0.00757
Opus 5 $0.00378 $0.00378
Sonnet 5 $0.00151 $0.00151
Haiku 4.5 $0.00076 $0.00076

Measured 4d ago against content hash a8f07ed3cda4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

clauder 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.

CLAUDE.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Instructions

Clauder - Persistent Memory MCP

This project uses clauder for persistent memory across Claude Code sessions.

CRITICAL: Call get_context at Session Start

IMPORTANT: You MUST call mcp__clauder__get_context at the START of every session to load:

  • Stored facts and decisions from previous sessions
  • User preferences and coding style guidelines
  • Unread messages from other Claude Code instances

This context may or may not be relevant to your tasks. You should not respond to this context unless it is highly relevant to your task.

Available Tools

  • mcp__clauder__remember: Store facts, decisions, or context
  • mcp__clauder__recall: Search and retrieve stored facts
  • mcp__clauder__forget: Delete a stored fact by ID (requires confirmation)
  • mcp__clauder__get_context: Load all relevant context for this directory (also shows sibling instances)
  • mcp__clauder__get_global_context: Load ALL facts across every directory/repository (use when you need context from other projects)
  • mcp__clauder__list_instances: List other running Claude Code sessions (grouped by directory)
  • mcp__clauder__send_message: Send messages to other instances (supports broadcast to directory)
  • mcp__clauder__get_messages: Check for incoming messages
  • mcp__clauder__rename_instance: Set or change THIS session's name on the fly (no restart) so other instances can discover and message it
Memory Management Tools
  • mcp__clauder__compact_context: Review all facts with age/size metadata for cleanup (supports global: true for all directories)
  • mcp__clauder__compress_facts: Atomically replace old facts with consolidated ones (delete + add in one transaction)
  • mcp__clauder__update_fact: Update an existing fact's content/tags in place (preserves ID and creation date)
  • mcp__clauder__fact_stats: Get statistics about stored facts (counts, sizes, age, per-directory breakdown)
  • mcp__clauder__purge_deleted: Permanently remove soft-deleted facts to reclaim space
  • mcp__clauder__bulk_forget: Delete multiple facts by IDs
  • mcp__clauder__bulk_remember: Store multiple facts in one call

Read the full file on GitHub · 50 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. 4d ago First seen · 50 lines · 757 tokens per session scan A a8f07ed3cda4

Subscribe to this mod's changes

clauder CLAUDE.md is an instructions file published in the GitHub repository MaorBril/clauder (53 stars, last pushed 1mo ago), licensed MIT. It adds 757 tokens to every session, about $0.0038 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 2026-08-30.

Related

Other instructions, from other repositories