AI-Cloud-Memory AGENTS.md

A set of repository instructions for AI-Cloud-Memory, a self-hosted service for shared AI memory, project boards, and roadmaps using Cloudflare and GitHub.

In plain words
What is it for?
It guides changes to the service, including tests, data exports, semantic search, integrations, and the required npm checks before merging.
Why use it?
It defines which data is authoritative, how users are isolated, what must stay private, and which optional services may be disabled.

Instructions file for CodexOpenCode

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/drewmauldin/ai-cloud-memory/agents-md
Clone the repo
git clone --depth 1 https://github.com/DrewMauldin/AI-Cloud-Memory

Made for: Codex, OpenCode.

Per session 129 This file is loaded in full into every session.
When invoked 129 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 $0.00129 $0.00129
Opus 5 $0.00064 $0.00064
Sonnet 5 $0.00026 $0.00026
Haiku 4.5 $0.00013 $0.00013

Measured yesterday against content hash 4184a79874ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

AI-Cloud-Memory 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 yesterday.

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.

AGENTS.md · 10 lines

What it actually says

Repository agent rules

  • Treat D1 as canonical and all vectors, exports and Markdown as rebuildable projections.
  • Keep every read and mutation owner-scoped by the authenticated numeric GitHub ID.
  • Never commit credentials, private memory content, real adopter identifiers or deployment URLs.
  • Preserve lexical-only operation when optional AI services are disabled.
  • Add tests for behavioural changes and run npm run check before merge.
  • Keep n8n, WebDAV, Obsidian, GitHub export and semantic search optional.
  • Do not add Codex automated code review to the product. Maintainers configure Codex Cloud externally at repository level.
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. yesterday First seen · 10 lines · 129 tokens per session scan A 4184a79874ac

Subscribe to this mod's changes

AI-Cloud-Memory AGENTS.md is an instructions file published in the GitHub repository DrewMauldin/AI-Cloud-Memory (0 stars, last pushed 2d ago), licensed MIT. It adds 129 tokens to every session, about $0.0006 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.