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-coding-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-coding-memory)<a href="https://agentmods.dev/skills/auuduu/dsh-timem-memory/timem-coding-memory"><img src="https://agentmods.dev/badge/skills/auuduu/dsh-timem-memory/timem-coding-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-coding-memory"><img src="https://agentmods.dev/badge/skills/auuduu/dsh-timem-memory/timem-coding-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 | $0.00122 | $0.01950 |
| Opus 5.5 | $0.00049 | $0.00780 |
| Sonnet 5.5 | $0.00024 | $0.00390 |
| Haiku 4.5 | $0.00012 | $0.00195 |
Grade A, and why
timem-coding-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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TiMEM Coding Memory（DSH 适配版）
domain=coding。服务器负责抽取事实并按历史去重——你的工作只是每个编码回合调用工具。
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。
每个编码回合（自动执行，无需用户要求）
1) mcp__timem__search_memories 探索性 grep/read 代码库之前 —— 即使直接读代码也行
2) 干活 对照代码/AGENTS.md 核实命中；count=0 时读 memory_gap / elevate_create
3) mcp__timem__create_memory 回答之后 —— 传 2-4 轮相关对话
不要等「remember / 请记住」才动。「我直接读仓库就行」不是跳过理由。 模块/架构/总览类问题也是编码回合 —— 先搜，不要跳过。
search_tier（简化版）
默认几乎总是 S3，仅两个例外：
| 时机 | search_tier |
|---|---|
| 默认 —— 任何已知仓库的编码回合 | S3 |
| 用户明确要求回忆（「你记得之前怎么定的吗」） | S0，limit=10 |
删除记忆之前（要先拿到 memory_id） |
S6 |
不确定时 → S3。
跳过（仅限窄范围）
| 跳过搜索 | 跳过写入 |
|---|---|
| 错别字 / 单行格式修改 | 未经证实的猜测（没读代码就总结） |
| 纯知识问答（「Python 列表推导语法」） | 临时调试状态（「断点在 L42」） |
| 用户说「别搜 / don't search」 | 与刚搜到的内容相比没有任何新东西 |
拿不准 → 搜。误报代价低，漏掉上下文代价高。
参数
| 字段 | 取值 |
|---|---|
domain |
coding |
session_id |
必填 —— 稳定的仓库/项目名（如 dsh、timem-mcp），绝不用随机 UUID |
query_text |
3-12 个任务导向的词（搜索必填） |
search_tier |
默认 S3；见上表 |
messages |
2-4 轮最近的 {role, content} 对话；不要贴整份文件或长日志 |
memory_hint |
可选 —— decision / constraint / lesson / convention / preference / correction |
AGENTS.md / CLAUDE.md —— 团队评审、长期稳定的约定。 TiMEM —— 智能体可检索的项目知识：决策、经验、偏好、经代码验证的模块/架构定位。
记忆 vs 规则： 事实/偏好/定位 → mcp__timem__create_memory；可复用的「情境 X 做 Y」→ mcp__timem__learn_rule（见 timem-rule-learning skill）。
场景边界
| 回合类型 | 使用 |
|---|---|
| 偏好 / 办公持久事实 / 主题背景 | timem-general-memory（domain=general） |
| 文案、语气、受众、草稿风格 | timem-writing-memory（domain=writing） |
| 仓库、调试、架构、模块问题 | 本 skill（domain=coding） |
拿不准：mcp__timem__classify_memory_scene(messages=[...])。
忘记
用户要求忘记 → mcp__timem__search_memories(search_tier="S6") 拿到 memory_id → 若歧义先与用户确认 → mcp__timem__delete_memory(memory_id="...")。
推荐调用形态
mcp__timem__search_memories(
query_text="<简洁的技术问题>", # 必填，3-12 词
domain="coding",
session_id="<仓库名>",
search_tier="S3",
limit=5,
)
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 · 150 lines · 122 tokens per session scan A a4f5a6a2faa8
timem-coding-memory is a skill published in the GitHub repository auuduu/dsh-timem-memory (0 stars, last pushed 2mo ago), licensed MIT. It adds 122 tokens to every session and 1,950 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.