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 skills/alenryuichi/openmemory-plus/memory-extractionnpx skills add Alenryuichi/openmemory-plus --skill memory-extractiongit clone --depth 1 https://github.com/Alenryuichi/openmemory-plusWrote 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/skills/alenryuichi/openmemory-plus/memory-extraction)<a href="https://agentmods.dev/skills/alenryuichi/openmemory-plus/memory-extraction"><img src="https://agentmods.dev/badge/skills/alenryuichi/openmemory-plus/memory-extraction.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 | $0.00052 | $0.03965 |
| Opus 5 | $0.00026 | $0.01982 |
| Sonnet 5 | $0.00010 | $0.00793 |
| Haiku 4.5 | $0.00005 | $0.00396 |
Grade A, and why
memory-extraction 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.
How it starts
The opening of the file, as written. The whole thing — 478 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Extraction Skill (Agent-Only)
目的
自动提取对话中的关键信息，智能路由到正确的存储系统：
- 项目级信息 →
_omp/memory/目录 (Git 版本控制) - 用户级信息 →
openmemoryMCP (跨项目共享)
Agent-Only 原则:
- 自动触发：对话结束时或检测到有价值信息时自动运行
- 智能分类：根据信息类型自动选择存储位置
- 零人工干预：无需用户确认，静默执行
- 双系统同步：同时管理
_omp/memory/和openmemory
核心目录结构
_omp/ # OpenMemory Plus 核心目录
├── commands/
│ ├── memory.md # 主命令入口
│ └── memory-actions/ # 7 个子动作
├── skills/
│ └── memory-extraction/ # 本 Skill
│ ├── SKILL.md
│ ├── scripts/validate.sh
│ └── templates/*.tmpl
└── memory/ # 项目级记忆
├── project.yaml # 项目配置 (SSOT)
├── decisions.yaml # 技术决策记录
├── changelog.yaml # 变更历史
└── sessions/ # 会话记录
双层记忆架构
| 系统 | 存储位置 | 用途 |
|---|---|---|
| 项目级 | _omp/memory/ |
项目配置、技术决策、变更记录 |
| 用户级 | openmemory MCP |
用户偏好、技能、跨项目上下文 |
分类规则
📖 详细规则: 参见
references/classification-rules.md
快速分类指南
| 信号 | Scope | Confidence | 存储位置 |
|---|---|---|---|
| "我喜欢/偏好/习惯" | PERSONAL | EXPLICIT | openmemory |
| "项目使用/配置为" | PROJECT | EXPLICIT | _omp/memory/ |
| "决定/选择/采用" | PROJECT | EXPLICIT | decisions.yaml |
| 用户反复使用某模式 | PERSONAL | INFERRED | openmemory |
| "试试/也许/可能" | EPHEMERAL | UNCERTAIN | 不存储 |
置信度阈值
- 存储阈值: confidence >= 0.4
- 自动存储: confidence >= 0.7
- 需确认: 0.4 <= confidence < 0.7
敏感信息过滤
禁止存储（检测后阻止）:
| 类型 | 检测模式 |
|---|---|
| API Key | sk-, api_key, token=, bearer |
| 密码 | password, secret, credential |
| 私钥 | -----BEGIN, PRIVATE KEY |
| 个人信息 | 身份证号, 银行卡号, 手机号 |
ROT 过滤规则
📖 详细规则: 参见
references/rot-filter.md
| 类型 | 检测方式 | 处理 |
|---|---|---|
| Redundant | 语义相似度 > 0.85 | 合并或跳过 |
| Obsolete | 超过 TTL 且无访问 | 标记或删除 |
| Trivial | 长度 < 10 或匹配阻止模式 | 丢弃 |
快速判断:
- ❌ "好的" / "OK" / "明白了" → Trivial
- ❌ 与已有记忆相似度 > 0.85 → Redundant
- ❌ 被明确否定的旧信息 → Obsolete
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 478 lines · 52 tokens per session scan A ddd4090b739b
memory-extraction is a skill published in the GitHub repository Alenryuichi/openmemory-plus (20 stars, last pushed 6mo ago), licensed MIT. It adds 52 tokens to every session and 3,965 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
a2wave-memory
Progressively recall and maintain a2wave cross-session memory through a compact startup catalog, bounded topics, and searchable history.
memorize
Curates insights from reflections and critiques into CLAUDE.md using Agentic Context Engineering.
memoryguard
Local-first MCP memory backend and governance console for coding agents. Auto-organize, quarantine, supersede, and rollback shared memories across multiple agents.
review-claude-code
Claude Code setup review (settings.json, permissions, rules, hooks, agents, memory, worktrees) against current official best practices. USE WHEN: user runs /review-claude-code or explicitly asks for this review. DO NOT USE WHEN: reviewing app code, other dev dependencies, or implementing features.
checkpoint
Save a session checkpoint — what was done, what's next, any blockers.
resume
Resume from last checkpoint — load full context and continue where you left off.