What is memorix CLAUDE.md?

Instructions for using Memorix, a cross-agent memory system for Claude Code. They explain when to search past project knowledge, when to save decisions and solutions, and how to handle retained memories.

Use them to search memory before decisions or feature work, record architecture choices and bug fixes, find known pitfalls, and manage memory retention.

They help an agent recover useful context from earlier sessions and preserve important decisions, fixes, and project details for later work.

How Tibu142/memorix configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Tibu142/memorix. 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/Tibu142/memorix/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Tibu142/memorix

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/tibu142/memorix/claude-md/github.svg)](https://agentmods.dev/instructions/tibu142/memorix/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/tibu142/memorix/claude-md"><img src="https://agentmods.dev/badge/instructions/tibu142/memorix/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/tibu142/memorix/claude-md"><img src="https://agentmods.dev/badge/instructions/tibu142/memorix/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 614 This file is loaded in full into every session.

When invoked 614 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	$0.00614	$0.00614
Opus 5.5	$0.00246	$0.00246
Sonnet 5.5	$0.00123	$0.00123
Haiku 4.5	$0.00061	$0.00061

Measured 2mo ago against content hash f1c3d2d309b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

memorix 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 2mo 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 · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memorix — Agent Instructions for Claude Code

You have access to Memorix, a cross-agent memory system. Use it to persist and recall project knowledge across sessions.

When to SEARCH memory (memorix_search)

Session start: Always search for recent context at the beginning of a conversation
Before making decisions: Search for past decisions on the same topic
When the user asks "remember"/"what did we"/"last time": Search for relevant history
Before implementing features: Check if similar work was done before
When encountering errors: Search for known gotchas and past solutions

When to STORE memory (memorix_store)

Architecture decisions: Why you chose X over Y (type: decision)
Bug fixes: Root cause and solution (type: problem-solution)
Gotchas/pitfalls: Things that tripped you up (type: gotcha)
How things work: Non-obvious system behavior (type: how-it-works)
Changes made: Significant code changes (type: what-changed)
Trade-offs: Compromises and their reasoning (type: trade-off)
Session goals: What the user asked for at session start (type: session-request)

When to check RETENTION (memorix_retention)

Periodically check which memories are stale or candidates for archiving
Review top-relevant memories to avoid duplicating past work

Best Practices

Be specific in titles: "Fixed Docker timeout from 30s to 60s" not "Fixed bug"
Include facts: Structured data like "Default port: 3001", "Retry count: 3"
Tag files: Always include filesModified when you edit files
Use concepts: Add searchable keywords for future retrieval
Don't over-store: Only store knowledge that would be useful in a future session
Entity naming: Use kebab-case descriptive names like "auth-module", "docker-config"

Tool Quick Reference

Tool	When	Example
`memorix_search`	Find past knowledge	`query: "authentication"`
`memorix_store`	Save new knowledge	`type: "decision", title: "Use JWT for auth"`
`memorix_detail`	Get full observation	`ids: [42, 43]`
`memorix_timeline`	See what happened around an event	`anchorId: 42`
`memorix_retention`	Check memory health	`action: "summary"`
`memorix_rules_sync`	Sync agent rules	`action: "status"`
`memorix_workspace_sync`	Migrate workspace configs	`action: "scan"`

Read the full file on GitHub · 48 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.

2mo ago First seen · 48 lines · 614 tokens per session scan A f1c3d2d309b1

Subscribe to this mod's changes

memorix CLAUDE.md is an instructions file published in the GitHub repository Tibu142/memorix (5 stars, last pushed 23d ago), licensed Apache-2.0. It adds 614 tokens to every session, about $0.0025 per session on Opus 5.5. 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 ai-coding ai-powered-knowledge-management claude-code-memory console cross-ide-sync cursor

memorix CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
memorix CLAUDE.mdTibu142/memorix	Instructions file	5	23d ago	Apache-2.0	A	614	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

memorix: Instructions file for Claude Code