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/yorha9e/moamcp/using-moamcpnpx skills add Yorha9e/moamcp --skill using-moamcpgit clone --depth 1 https://github.com/Yorha9e/moamcpWrote 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/yorha9e/moamcp/using-moamcp)<a href="https://agentmods.dev/skills/yorha9e/moamcp/using-moamcp"><img src="https://agentmods.dev/badge/skills/yorha9e/moamcp/using-moamcp.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 | $0.00097 | $0.01721 |
| Opus 5 | $0.00048 | $0.00860 |
| Sonnet 5 | $0.00019 | $0.00344 |
| Haiku 4.5 | $0.00010 | $0.00172 |
Grade A, and why
using-moamcp 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 6d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
using-moamcp — Tips 与共享黑板使用规范
moamcp 提供两层跨 Session 记忆，底层是同一套 BoardStore（append-only JSONL、键级 last-write-wins、墓碑删除），上层分型：
- Project Tips（
moa_tip_*）：项目级、跨 Session 持久化的功能想法与上下文卡片，有明确 schema（title/summary/context/status/module/tags/documentRefs/...），是第一优先级的用户功能。写在哪：tips/<id>。 - Raw Board（
moa_board_*）：无类型约束的通用逃生口，给 Agent 和高级用户共享契约、决策、状态、指针。直接写任意 key。
1. workspace 传参铁律
moa_tip_* 全部工具，以及 moa_board_* 中 scope: "workspace"（含缺省）的调用，必须传 workspace 参数，取值是系统提示中当前 Working Directory 的绝对路径。
- 永远不要用 moamcp 进程自己的 cwd 当 workspace——Kimi 插件运行时 MCP 进程的 cwd 是插件根（
plugins/managed/moamcp/），不是项目根。 - 不确定时先读取系统提示确认当前 Working Directory，再原样传入；不要猜、不要相对化、不要带尾随分隔符的重复。
scope: "global"与scope: "task:<id>"不需要 workspace；moa_board_wait等 workspace 作用域调用同样要传。
2. 不静默保存：先草案，后确认
新建 Tip 或对现有 Tip 做重大更新（status 变更、context/summary 重写、documentRefs 调整）前，必须先整理草案并让用户确认，确认后才调用工具：
- 从当前讨论整理：
title（简短）、summary（几句话的目标与预期价值）、context（4–8 KiB 以内的大概背景，不复制完整对话）、status（默认captured）、module/tags、documentRefs/sourceRefs/relatedTipIds（如有）。 - 把草案展示给用户，说明"保存为项目级 Tip，跨 Session 可见"。
- 用户明确确认后再调用
moa_tip_create/moa_tip_update（都传workspace）。
绝不静默保存：未经确认不得把对话内容写入 Tips；用户只是闲聊或临时提问时也不得主动落盘。
3. Session 启动不自动扫描
本插件通过 sessionStart.skill 注入本规范，不代表要自动加载数据。Session 开始时：
- 不要自动调用
moa_tip_list/moa_tip_read/moa_board_*把全部 Tips 或黑板内容读进上下文； - 不要向用户主动播报全部 Tips 列表；
- 只在当前任务确实需要时按需查询。
4. 按任务检索：先 list，再选择性 read
需要 Tips 或黑板内容时：
- 先
moa_tip_list（可用status/tags/module过滤，缺省不返回已归档），或moa_board_list轻量浏览 key 列表； - 从命中项里只对与当前任务相关的条目
moa_tip_read/moa_board_read取完整内容； - 避免一次读回全部条目浪费上下文。
5. 普通临时对话不入 Tip
- 一次性执行指令 → 宿主 TodoList 或 dispatch prompt，不进 Tip；
- 大段代码/长文档 → 项目文件，Tip 里只留路径指针；
- 只有用户明确表示要记住的功能想法、设计动机、讨论结论和跨 Session 背景才进 Tip。
6. 工具与命令速查
Tips 工具（5 个，均需 workspace）：
| 工具 | 用途 |
|---|---|
moa_tip_list |
按 status/tags/module 过滤列出（不返回完整 value） |
moa_tip_read |
读取单个 Tip 完整内容 |
moa_tip_create |
新建 Tip（先给用户确认草案） |
moa_tip_update |
更新字段或 status（重大变更先确认） |
moa_tip_archive |
归档，不再出现在默认列表（历史保留） |
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.
- 6d ago First seen · 94 lines · 97 tokens per session scan A 46c8087ed676
using-moamcp is a skill published in the GitHub repository Yorha9e/moamcp (2 stars, last pushed 10d ago), licensed MIT. It adds 97 tokens to every session and 1,721 once invoked, about $0.0005 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 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.