Borrowing it
Nothing to install: this file belongs to BeWaterMyFriend7/SKILL-PROJECT. 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/BeWaterMyFriend7/SKILL-PROJECT/main/.opencode/skills/agent-offline-mermory/SKILL.mdgit clone --depth 1 https://github.com/BeWaterMyFriend7/SKILL-PROJECTWrote 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/bewatermyfriend7/skill-project/agent-offline-mermory)<a href="https://agentmods.dev/skills/bewatermyfriend7/skill-project/agent-offline-mermory"><img src="https://agentmods.dev/badge/skills/bewatermyfriend7/skill-project/agent-offline-mermory/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/skills/bewatermyfriend7/skill-project/agent-offline-mermory"><img src="https://agentmods.dev/badge/skills/bewatermyfriend7/skill-project/agent-offline-mermory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00198 | $0.03666 |
| Opus 5 | $0.00099 | $0.01833 |
| Sonnet 5 | $0.00040 | $0.00733 |
| Haiku 4.5 | $0.00020 | $0.00367 |
Grade A, and why
agent-offline-mermory 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 11d 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 — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Offline Mermory
管理本地的 AI 协作记忆，支持两种记忆根目录：Obsidian 仓库（默认校验 .obsidian）和纯 Markdown 文件夹。这个 Skill 有两种触发模式：明确触发模式负责写入和主动查询；自动回忆模式只负责在相似技术流程前只读检索经验。
首次使用必读：初始化
安装后必须初始化记忆根目录，否则查询和写入都会被拒绝。未初始化时不得自动猜测路径，必须停下，优先用对话引导用户完成初始化。初始化只需确认三件事：
- 记忆根目录绝对路径；
- 是否要求位于 Obsidian 仓库内（
require_obsidian，默认true，可选false使用纯文件夹）； - 经验加载模式（
experience_mode，默认auto，可选manual）。
推荐按以下顺序选择初始化方式：
方式一：对话初始化（首选）
用户只需要说“初始化 agent-offline-mermory”或首次使用时要求查询/写入，Agent 通过对话确认上面三件事（例如：请用户提供或帮助选择记忆根目录路径，确认是否使用 Obsidian，确认经验模式），然后代为调用写入器完成初始化。全程用户不需要敲任何命令。完成后用中文向用户报告记忆根目录、模式选择和后续用法。
方式二：命令行交互式
用户运行短命令，写入器会逐步提问（路径、是否 Obsidian、经验模式），不需要一次输入所有参数：
& "<Skill目录>\scripts\write-memory.ps1" -Action Init
sh "<Skill目录>/scripts/write-memory.sh" --action init
方式三：编辑配置文件
- 将
settings.example.json复制为settings.json； - 修改其中的
memory_root（记忆根目录绝对路径）、require_obsidian、experience_mode； - 在终端运行
-Action Init（短命令）交互确认，或让 Agent 读取配置后代为完成初始化。
初始化会创建 Inbox、Tasks、Knowledge 三个目录、一个与记忆根目录同名的入口文档，以及各目录的 _index.md 索引。之后每次写入或更新记录，写入器会自动刷新 Tasks/ 和 Knowledge/ 的索引。
经验加载模式
auto（默认）：当前任务确实涉及 Git、代码修改、测试、构建、部署、环境配置、迁移或其他可重复技术流程时，执行一次只读检索Knowledge，严格相关性过滤、最多 3 条，作为风险提醒；不写入任何内容。manual：只有用户明确调用$agent-offline-mermory时才加载经验，其余任务完全不检索，减少不必要的调用和 token 消耗。- 对话内可临时覆盖：用户说“这次不用加载经验”时，单次跳过检索，不需要改配置。
- 修改方式：通过对话让 Agent 重新执行
init，或运行set-root/SetRoot短命令，写入器会沿用已有配置并逐步提问。
判断触发模式
- 明确触发包括：用户输入
$agent-offline-mermory、从 Skill 菜单选择本 Skill，或明确说“使用 agent-offline-mermory”。明确触发后，除纯状态查询和初始化外，先执行一次相关经验预检，再按用户要求执行写入或主动查询。 - 自动回忆（仅
auto模式）只在当前任务确实涉及 Git、代码修改、测试、构建、部署、环境配置、迁移或其他可重复技术流程时执行，并且只能查询Knowledge；manual模式下不得执行自动回忆。 - 自动回忆模式不得写入、更新、初始化或修改任何文件，也不得查询
Tasks或Inbox。 - 普通的“总结一下”“记住这个”“有哪些待办”或“某类操作有哪些经验”等请求，如果没有明确触发，只在当前上下文中回答，不读取记忆目录。
- 不得写入已配置记忆根目录之外的位置。
- 不得自行推断应该更新某个已有任务或知识文档。
- 仅当用户明确提供文件路径、准确文档名或 Obsidian 链接时，才更新已有文档。
自动回忆的查询失败、配置不存在或没有高相关结果时，继续当前任务，不创建记录，也不把失败升级为写入请求。只有检索结果与当前操作明确相关时，才将其压缩成风险提醒并应用；不得让历史经验覆盖当前仓库、当前命令或用户的明确要求。
What ships with it
9 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.
- agents/openai.yaml 300 B
- assets/templates/dashboard.md 498 B
- assets/templates/inbox-entry.md 43 B
- assets/templates/knowledge-note.md 106 B
- assets/templates/task-handoff.md 116 B
- scripts/write-memory.ps1 2.6 KB runs code
- scripts/write-memory.py 25 KB runs code
- scripts/write-memory.sh 589 B runs code
- settings.example.json 219 B
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.
- 11d ago First seen · 299 lines · 198 tokens per session scan A 7b3da71710ac
agent-offline-mermory is a skill published in the GitHub repository BeWaterMyFriend7/SKILL-PROJECT (51 stars, last pushed 3d ago), licensed Apache-2.0. It adds 198 tokens to every session and 3,666 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.