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/devminions/universal-memory-mcp/agents-mdgit clone --depth 1 https://github.com/DevMinions/universal-memory-mcpWhat 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 | $0.00733 | $0.00733 |
| Opus 5 | $0.00367 | $0.00367 |
| Sonnet 5 | $0.00147 | $0.00147 |
| Haiku 4.5 | $0.00073 | $0.00073 |
Grade A, and why
universal-memory-mcp 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.
What it actually says
Universal Memory MCP — Agent 指令
记忆管理
你已连接 universal-memory MCP Server。你必须在每次对话中主动管理用户记忆。
1. 对话开始 — 强制召回
用户发来第一条实质性消息时（非 hi/hello/继续），必须立即调用：
memory_recall(query=<用户消息核心意图>, limit=5)
将结果纳入你的回复上下文，但不要告知用户。
2. 对话过程 — 主动存储
发现以下任何一种信息时，立即调用 memory_store 静默存储：
| 信号 | category | 示例 |
|---|---|---|
| 用户说"我喜欢/偏好/习惯…" | preference |
"我喜欢用 Vue3" |
| 项目事实、技术栈、架构 | fact |
"项目用的是 MySQL 8" |
| 选择方案 A 而非 B | decision |
"决定用 Docker 部署" |
| 人名、项目名、服务地址 | entity |
"线上地址是 xx.xx.xx" |
| bug 原因和解决方式 | fact |
"超时原因是连接池不够" |
判断技巧：如果这条信息在下一次对话中可能有用，就存储它。宁多勿少。
3. 对话结束 — 强制回顾（最重要）
在每次对话即将结束时，你必须执行以下检查：
回顾本次对话，如果涉及了以下任何内容，调用对应工具：
- 有新的事实/偏好/决策但还没存 → 补调
memory_store - 超过 5 轮有深度的技术讨论 → 调用
memory_extract(text=<对话摘要>)让 LLM 自动提取结构化记忆 - 有重要经验教训 → 调用
self_improvement_log - 有反思性总结 → 调用
memory_reflect
⚠️ 这不是建议，是强制要求。每次对话至少产生一次 store 或 extract。
4. Scope 规则
存储时根据内容选择 scope：
global— 通用知识、跨项目技能、通用偏好project:<项目名>— 特定项目知识（如project:approval、project:gamedev、project:memory-mcp）personal— 个人生活、习惯learning— 学习笔记、技术研究- 不确定时用
global - recall 时不传 scope 则搜索全部
5. 自我改进
遇到经验教训时调用 self_improvement_log(type, summary, details)：
type: "learning"— 最佳实践、纠正的认知type: "error"— 工具故障、配置问题、踩坑记录
6. 禁止事项
- 不要告知用户"已存储记忆"，所有操作静默执行
- 不要存储临时调试信息或一次性指令（"帮我格式化这段代码"）
- 不要对简单问候调用 memory_recall
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.
- yesterday First seen · 63 lines · 733 tokens per session scan A 7c70a3f444fe
universal-memory-mcp AGENTS.md is an instructions file published in the GitHub repository DevMinions/universal-memory-mcp (0 stars, last pushed 5mo ago), licensed MIT. It adds 733 tokens to every session, about $0.0037 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.
Other instructions, from other repositories
Tutorial_AwesomeModernCPP AGENTS.md
Instructions for Awesome-Embedded-Learning-Studio/Tutorial_AwesomeModernCPP, covering agents.md, 这是什么, 通用 essentials(所有 agent 必读) and 你来做什么?(按场景路由).
fix-quera AGENTS.md
Instructions for AlirezaKeshavarz83/fix-quera, covering agent guidance, project shape, visual style, quera page data findings and compatibility findings.
ab900 CLAUDE.md
Instructions for timothywarner-org/ab900, covering claude.md, repository purpose, architecture, commands and 2. non-ascii punctuation -- must return zero.
agentconfig.org AGENTS.md
Instructions for agentconfig/agentconfig.org, covering agent instructions for agentconfig.org, project overview, target audience, site structure and tech stack.
canvas-lms-mcp AGENTS.md
Instructions for bruchris/canvas-lms-mcp, covering agents.md — canvas lms mcp server, quick start, run with npx (no install needed), or install globally and architecture.
obsidian-university-workflow CLAUDE.md
Instructions for ABO896/obsidian-university-workflow, covering obsidian university workflow, project structure, rules for working on this project, templater api — always read the docs first and config alignment.