MemoraX Code is a shared memory layer for AI coding agents that stores and recalls repository knowledge, engineering lessons, and working preferences across sessions. It helps developers avoid repeating context when working with Codex, Claude Code, and other supported agents. The catalogue entries provide hooks, instructions, skills, and a plugin for using MemoraX Code.
Borrowing it
Nothing to install: this file belongs to memorax-ai/memorax-code. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/memorax-ai/memorax-code/main/AGENTS.mdgit clone --depth 1 https://github.com/memorax-ai/memorax-codeWrote 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/memorax-ai/memorax-code/agents-md)<a href="https://agentmods.dev/instructions/memorax-ai/memorax-code/agents-md"><img src="https://agentmods.dev/badge/instructions/memorax-ai/memorax-code/agents-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.
<a href="https://agentmods.dev/instructions/memorax-ai/memorax-code/agents-md"><img src="https://agentmods.dev/badge/instructions/memorax-ai/memorax-code/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01280 | $0.01280 |
| Opus 5.5 | $0.00512 | $0.00512 |
| Sonnet 5.5 | $0.00256 | $0.00256 |
| Haiku 4.5 | $0.00128 | $0.00128 |
Grade A, and why
memorax-code AGENTS.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 28d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MemoraX Code Agent Guide
These are mandatory working rules for coding agents. Use CONTRIBUTING.md for development and verification procedures and ARCHITECTURE.md for system boundaries. Current user instructions, live source, and executable tests take precedence over memory.
1. Start Safely
- Run
git status --short --branch; confirm the intended worktree and preserve unrelated tracked, untracked, and staged changes. - Read nearby implementation and tests. Keep changes focused; do not mix unrelated formatting, renaming, dependencies, or lockfile rewrites, or run broad auto-fix commands without need.
- Use English for source identifiers, comments, docstrings, and canonical documentation. Synchronize both README files when shared content changes.
- Treat
.repo_memory/as Git-ignored retrieval guidance, not code authority; never publish it.
2. Architecture Routing
Read ARCHITECTURE.md before changing module or test placement, entrypoints, control/data flow, state or authority, packaging/materialization, or cross-package or cross-capability dependencies. Preserve its boundaries; intentional changes must update the architecture and affected executable contracts in the same change.
3. Hook, Session, and Scope Invariants
- Version and client-qualify Hook commands. Validate required session, turn, and prompt correlation at HTTP ingress; incomplete, conflicting, unknown, or client-inapplicable identities fail closed.
- Automatic writeback uses only the matching client's
native content authority.
Hook/plugin text is never a fallback outside Trae's validated
UserPromptSubmit/Stopprimary-authority exception. Trace, latest-turn guesses, and another client's format are never fallbacks. - Include the client in session, turn metadata, trace, and operational identity. Equal native IDs across clients must stay isolated.
- For a fixed Base User ID, pin each live session to its workspace and
repository scope. Linked worktrees may share repository scope; unrelated
repositories and genuine non-Git workspaces keep separate local identity.
Only the documented malformed/incomplete direct-
.gitexception may use local-folder scope, then upgrade in-session to verified Git scope for the same Base User ID and canonical workspace root; discard pending fallback writeback on upgrade. Other missing, unreadable, malformed, or conflicting scope authority must not silently fall back or rebind. A changed Base User ID requires a new binding; existing Turn metadata must still pass scope validation. - Derive repository identity read-only, without executing Git. Preserve path canonicalization, Git marker validation, symlink/junction containment, and fail-closed behavior.
- For completed content, consume matching turn metadata only after local writeback enqueue acceptance. Rejection, missing content, interruption, and concurrent replacement require explicit retention or discard reasons.
- Use versioned private authority for Backend connection, token, PID, Hook generation, and lifecycle records. Cross-process read/modify/write needs bounded locking or equivalent version validation, not only in-memory queues.
- Keep the Backend on loopback by default; external binding requires explicit opt-in and authentication.
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.
- 28d ago Changed · +4 lines · +68 tokens per session 8c1baf1f6887
- 1mo ago Changed · -39 lines · -445 tokens per session 0db23848c208
- 1mo ago Changed · +9 lines · +138 tokens per session db74ac93c306
- 1mo ago First seen · 132 lines · 1,519 tokens per session scan A 21e793e2f5ae
memorax-code AGENTS.md is an instructions file published in the GitHub repository memorax-ai/memorax-code (1,999 stars, last pushed today), licensed MIT. It adds 1,280 tokens to every session, about $0.0051 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 2026-08-30.
Other instructions, from other repositories
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.