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 auuduu/dsh-timem-memory --skill timem-general-memorygit clone --depth 1 https://github.com/auuduu/dsh-timem-memoryWrote 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/auuduu/dsh-timem-memory/timem-general-memory)<a href="https://agentmods.dev/skills/auuduu/dsh-timem-memory/timem-general-memory"><img src="https://agentmods.dev/badge/skills/auuduu/dsh-timem-memory/timem-general-memory/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/auuduu/dsh-timem-memory/timem-general-memory"><img src="https://agentmods.dev/badge/skills/auuduu/dsh-timem-memory/timem-general-memory.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00130 | $0.01433 |
| Opus 5.5 | $0.00052 | $0.00573 |
| Sonnet 5.5 | $0.00026 | $0.00287 |
| Haiku 4.5 | $0.00013 | $0.00143 |
Grade A, and why
timem-general-memory 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 1mo 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TiMEM General Memory(DSH 适配版)
domain=general。服务器负责抽取事实并按历史去重——你的工作只是每个回合调用工具。
可用性检查
TiMEM 工具在 DSH 中以 mcp__timem__* 命名(mcp__timem__search_memories、mcp__timem__create_memory 等)。
若工具列表中不存在这些工具,说明 TiMEM MCP 未连接——跳过本 skill,不要猜别的工具名。
每个回合(自动执行,无需用户要求)
1) mcp__timem__search_memories 回答之前 —— 即使用户没说 remember/记得
2) 作答 使用相关命中;忽略噪音;过期则弃用
3) mcp__timem__create_memory 回答之后 —— 传 2-4 轮最近对话
不要等「remember / 记住」才动。不要因为「直接能答」就跳过。「这是工作不是私事」不是跳过理由。
跳过(仅限窄范围)
| 跳过搜索 | 跳过写入 |
|---|---|
| 纯知识问答(「今天星期几」) | 纯情绪 / 一次性闲聊(「今天有点累」) |
| 用户说「别搜 / don't search」 | 与刚搜到的内容相比没有任何新东西 |
| 只有过程叙述、没有持久结论 |
拿不准 → 搜。误报代价低,漏掉上下文代价高。
参数
| 字段 | 取值 |
|---|---|
domain |
general |
session_id |
偏好/身份用 personal;办公话题用稳定主题名(如 timem-product、acme-q3)。永远不要省略,永远不要用随机 UUID |
query_text |
3-12 个任务导向的词(搜索必填) |
messages |
2-4 轮最近的 {role, content} 对话;不要贴长日志 |
记忆 vs 规则: 事实/偏好/背景 → mcp__timem__create_memory;可复用的「情境 X 做 Y」→ mcp__timem__learn_rule(见 timem-rule-learning skill)。
什么属于这里
- 个人偏好、角色/背景
- 持久的办公/主题事实 —— 决策、负责人、截止日期、会议结论、跨会话仍然有用的产品/项目事实
- 不属于编码、不属于文案的生活/工作背景
不属于: 工作流水账、过程叙述、临时进行中的状态。静态规则 → AGENTS.md / CLAUDE.md。
场景边界
| 回合类型 | 使用 |
|---|---|
| 仓库、调试、架构 | timem-coding-memory(domain=coding) |
| 文案、语气、受众、草稿风格 | timem-writing-memory(domain=writing) |
| 偏好 / 办公持久事实 / 主题背景 | 本 skill(domain=general) |
拿不准:mcp__timem__classify_memory_scene(messages=[...])。
忘记
用户要求忘记 → mcp__timem__search_memories 先搜 → 若歧义先确认 → mcp__timem__delete_memory(memory_id="...")。
推荐调用形态
mcp__timem__search_memories(
query_text="<3-12 个任务导向的词>",
domain="general",
session_id="personal", # 或稳定主题名
limit=5,
)
mcp__timem__create_memory(
domain="general",
session_id="personal", # 或稳定主题名
messages=[2-4 轮最近的 user/assistant 对话],
)
示例
例 1 — 偏好回忆(搜索 + 写入)
用户:「你记得我喜欢什么样的回答风格吗?」
mcp__timem__search_memories(query_text="回答风格 偏好", domain="general", session_id="personal", limit=5) → 核实 → 作答 → mcp__timem__create_memory(session_id="personal", messages=[本轮对话])。
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.
- 1mo ago First seen · 124 lines · 130 tokens per session scan A bb5eda6be733
timem-general-memory is a skill published in the GitHub repository auuduu/dsh-timem-memory (0 stars, last pushed 2mo ago), licensed MIT. It adds 130 tokens to every session and 1,433 once invoked, about $0.0005 per session on Opus 5.5. 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
causal-memory
Causal memory for agents — install/setup the causal-memory MCP server, then record decisions/outcomes and recall them before acting. Trigger when the user asks to install or set up causal-memory/agent memory, when causal-memory MCP tools are available and the agent faces a non-trivial decision (architecture, debugging…
event-review
A weekly review process for event logs and leftover task records, turning repeated problems or useful lessons into proposed memory, knowledge, or skill entries.
handoff
Compact the current conversation into a handoff document for another agent to pick up.
memory-system
A guide to giving an AI agent persistent, user-specific memory across conversations. It covers what to remember, how to store it, how to update or compress it, and when to use memory instead of a shared knowledge base.
memanto-companion
Inspect and manage the cross-session engineering memory that Memanto maintains for your Claude Code skills. Use when the user asks what Memanto remembers, wants to see their engineering profile, manually recall context for a skill, or store a decision. The automatic lifecycle hooks handle capture/injection on their…
openlore
Query and publish to an OpenLore knowledge repository over SSH using ordinary shell commands. Use when a task needs project documentation, runbooks, shared team knowledge, or a place to publish findings.