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/avids2/memorix/claude-mdgit clone --depth 1 https://github.com/AVIDS2/memorixWrote 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/avids2/memorix/claude-md)<a href="https://agentmods.dev/instructions/avids2/memorix/claude-md"><img src="https://agentmods.dev/badge/instructions/avids2/memorix/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 | $0.01073 | $0.01073 |
| Opus 5 | $0.00536 | $0.00536 |
| Sonnet 5 | $0.00215 | $0.00215 |
| Haiku 4.5 | $0.00107 | $0.00107 |
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 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 — 96 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, an open-source cross-agent memory layer for coding agents via MCP. Use it to persist and recall project knowledge across sessions, preserve reasoning, and retrieve Git-backed engineering truth when relevant.
Using Memorix Memory Tools
This project has Memorix MCP tools available for persistent cross-session memory.
For broad continuation or a fresh handoff, start with Memory Autopilot before progress files, dev-log reads, ad-hoc file reads, or git archaeology:
- MCP:
memorix_project_contextwith the current task - Default first step for non-trivial coding work: call
memorix_project_contextwith the user's actual task. Memorix will choose a task-lensed brief (bugfix, feature, release, onboarding, refactor, docs, test, or general). Treat its "Start here" files as the first project files to inspect. - Claude Code exposes MCP tools through dynamic tool loading. If the tool is not directly visible in the first tool list, search/select the Memorix project context tool before using shell fallback.
- CLI fallback: only after MCP is confirmed unavailable, run
memorix context --task "<current task>"from the shell instead of skipping memory or hand-writing tool calls - Do not skip project memory just because the initial MCP status says
pending
Claude Code starts MCP servers asynchronously. An initial pending MCP status is
not a failure by itself; the tools may appear through dynamic tool loading after
startup. The reliable user-facing fallback is the memorix context CLI command,
but fallback should come after the MCP-first attempt.
When to search memory
Use memorix_search when prior project context would help — for example:
- The user asks about a past decision, bug, or change
- You need to understand why something was designed a certain way
- You're continuing work that started in a previous session
You do not need to search memory for simple, self-contained tasks.
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 · 96 lines · 1,073 tokens per session scan A ba79fe1dfcc6
memorix CLAUDE.md is an instructions file published in the GitHub repository AVIDS2/memorix (705 stars, last pushed 4d ago), licensed Apache-2.0. It adds 1,073 tokens to every session, about $0.0054 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.
Other instructions, from other repositories
mcp-server-azure-devops copilot-instructions.md
Instructions for Tiberriver256/mcp-server-azure-devops, covering azure devops mcp server - development instructions, prerequisites, building and running, 1. install dependencies and 2. build the server.
mcp-server-azure-devops AGENTS.md
Instructions for Tiberriver256/mcp-server-azure-devops: /home/tiberriver256/repos/mcp-server-azure-devops/docs/important-knowledge/azure-devops-rest-api-research.md Researching Azure DevOps REST APIs, selecting api-version, or handling Azure DevOps Server (on-prem) endpoints.
Ctxo CLAUDE.md
Instructions for alperhankendi/Ctxo, covering claude.md — ctxo, project overview, quick reference, dev (pnpm workspace) and usage (consumer).
draft CLAUDE.md
Instructions for drafthq/draft, covering claude.md, repository overview, build & test commands, run a single test and etc. — any test in tests/ is independently executable.
specops CLAUDE.md
Instructions for sanmak/specops, covering claude.md, what is specops, build & validate commands, run all tests (single command) and generate for a single platform.
Ctxo copilot-instructions.md
Instructions for alperhankendi/Ctxo, covering ctxo mcp tool usage (mandatory), before any code modification, before starting a task, before reviewing a pr or diff and when exploring or searching code.