timem-general-memory

timem-general-memory is a skill for Claude Code, Codex from auuduu/dsh-timem-memory. It costs 130 tokens per session (1,433 once invoked), scanned A, original, MIT.

A workflow for storing and retrieving long-term personal, work, and project context. It searches general memories before a response and saves lasting facts afterward when TiMEM is connected.

In plain words
What is it for?
Use it to recall relevant personal or work context and record durable facts that should be remembered later.
Why use it?
It keeps useful background such as preferences, decisions, responsibilities, and deadlines available across conversations.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

Good fit Use it to recall relevant personal or work context and record durable facts that should be remembered later.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/auuduu/dsh-timem-memory/timem-general-memory
Install

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.

Any agent
npx skills add auuduu/dsh-timem-memory --skill timem-general-memory
Clone the repo
git clone --depth 1 https://github.com/auuduu/dsh-timem-memory

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for timem-general-memory

README.md
[![agentmods](https://agentmods.dev/badge/skills/auuduu/dsh-timem-memory/timem-general-memory/github.svg)](https://agentmods.dev/skills/auuduu/dsh-timem-memory/timem-general-memory)
Your own site
<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.

agentmods 80×15 button for timem-general-memory

Your own site · 80×15
<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>
Per session 130 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,433 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 1mo ago against content hash bb5eda6be733, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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.

skills/timem-general-memory/SKILL.md · 124 lines

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])。

Read the full file on GitHub · 124 lines

Changes

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.

  1. 1mo ago First seen · 124 lines · 130 tokens per session scan A bb5eda6be733

Subscribe to this mod's changes

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.

Related

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…

JingxuanC/causal-memory · 88 tokens

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.

reatcat/l123-harness · 92 tokens

handoff

Compact the current conversation into a handoff document for another agent to pick up.

gongyijie85/mattpocock-skills-dsh · 19 tokens

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.

bojieli/ai-agent-book · 95 tokens

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…

moorcheh-ai/memanto · 72 tokens

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.

aakarim/OpenLore · 42 tokens