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 skills add Holden323/ldm-skill --skill ldm-memory-systemgit clone --depth 1 https://github.com/Holden323/ldm-skillWrote 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/holden323/ldm-skill/ldm-memory-system)<a href="https://agentmods.dev/skills/holden323/ldm-skill/ldm-memory-system"><img src="https://agentmods.dev/badge/skills/holden323/ldm-skill/ldm-memory-system.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 5.1 | $0.00195 | $0.02495 |
| Opus 5 | $0.00097 | $0.01247 |
| Sonnet 5 | $0.00039 | $0.00499 |
| Haiku 4.5 | $0.00019 | $0.00249 |
Grade A, and why
ldm-memory-system 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 3d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ldm-memory-system：认知资产统一治理
定位：交接skill让你的AI不失忆，本skill让它不失智。 哲学：Memory是指针，不是数据库；治理是统一的，不分类目。
一、统一治理四问（外壳）
所有类目——Memory条目、文档、Skill、指针——过同一套四问：
① 住哪层？ 该在 Skill / 文档 / Memory 哪层？住错层 → 降级或上收
② 真源在哪？ 唯一真源是哪个文件？副本失效 → 删副本；真源失效 → 修真源
③ 还准吗？ 指向的东西还在吗？计数对吗？项目还活着吗？→ 当场验证
④ 有索引吗？ 所在目录有README吗？长文档有##章节吗？skill有description吗？
没有 → 黑数据，补索引
为什么四问能统一？ 治理的本质就这四件事，不分类目。同一套问题，换个对象而已。
四问 × 类目矩阵
| 类目 | ①住哪层 | ②真源在哪 | ③还准吗 | ④有索引吗 |
|---|---|---|---|---|
| Memory条目 | 三选一 | 看内容类型 | fetch/stat当场验证 | 指针→指向有索引的文档 |
| 文档 | 文档层 | 自身或上级文档 | 版本号检查 | 目录README + ##章节 |
| Skill | Skill层 | 本地真源目录 | 流程/轮换表最新？ | frontmatter的description |
| 指针 | 各层 | 指向的目标文件 | 目标还存在吗 | 目标有索引吗 |
二、内核：三层架构 + SOT链 + B级分级（原创，重构不动）
三层架构（地图：知识放哪个仓库）
| 层 | 存什么 | 粒度 | 容量 |
|---|---|---|---|
| Skill（操作手册） | 可复用操作手册、教训集、完整流程 | 完整文档 | 无限 |
| 文档系统（项目资料库） | 项目详情、成稿、表格、选题库 | 按项目分文件夹 | 无限 |
| Memory（随身小本子） | 铁律、进度数字、路由指针 | 一行一条，§分隔 | ~2000字符 |
红线：对话原文→聊天记录存档；临时状态→会话搜索；完整key/完整路径→配置文件。都不许进Memory。
SOT链（法律：每条知识只有一个真身）
Skill > 本地md文档 > 聊天存档 > Memory
- 一条知识只能住一层（真源层），其他层最多留指针
- 更新时改真源层，禁止平行开副本
- 写入前先问：这知识最后会不会被纠正？会 → 放能被纠正的那层
B级分级（包装：Memory条目写成什么样）
- B级为标准格式：结论 + 关键数字 + 推导逻辑概要
- 不存纯结论（缺推导，未来无法判断还适不适用）
- 不存完整表格（放项目目录，Memory只留一行指针）
- 进度数字A级即可（无歧义的纯数字）；铁律/指针/环境配置用B级
容量红线（预算驱动，2026-09-01补）
四问是逐条判定（这条该不该留），容量红线是预算驱动（memory总共只准住多少）——两者配合，缺一压不动：
- 70%黄线：新知识进memory前，必须先淘汰等量旧知识（有进有出），禁止只进不出
- 85%红线：触发深度治理——教训类条目一律上收进对应skill（SOT链强制：教训真源=skill层），memory不留教训全文副本，只留半句指针"教训已进XX skill"。淘汰判据：①已上收进skill/文档 ②30天未再触发 → 进删除候审单
- 深度治理顺序：先写入skill（教训搬家）→ 用户拍板 → 删memory副本 → 验证水位报告
三、两阶段
阶段一【搭建】：从零建这套系统
适用：新用户第一次搭建；或系统混乱（无索引/无分类/不知道哪些该升级）。
先问3个问题（决定结构深度和毕业判断）：
- 你有哪几个长期项目？（决定文档层怎么分文件夹）
- 哪些文件最常被引用？（决定哪些要建索引）
- 哪些操作反复做过3次以上？（决定哪些该毕业成skill）
然后按五步搭建（详见 references/setup-guide.md）：
- 画三层结构图（用用户自己的项目举例）
- 建文档层：按项目建文件夹 + 每目录一个README + 长文档##章节
- 建Memory层：清点现有条目 → 四问归类 → B级格式重写 → 不存key/完整路径
- 定毕业标准（见第四章）
- 试跑验证：搭完跑一次维护扫描，确认结构能用
最小可行版：怕复杂的新用户，只搭 Memory 分类 + 根目录README，文档层和skill层用到再建。不强制一次搭完。
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.
- 3d ago Changed · +8 lines 7bc17ef57220
- 7d ago First seen · 147 lines · 195 tokens per session scan A 528fe226ba1b
ldm-memory-system is a skill published in the GitHub repository Holden323/ldm-skill (31 stars, last pushed 5d ago), licensed MIT. It adds 195 tokens to every session and 2,495 once invoked, about $0.0010 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 skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.