limem.remember

limem.remember is a skill for Claude Code from gaooooosh/limem-agent-plugin. It costs 125 tokens per session (1,671 once invoked), scanned A, original, MIT.

A skill for saving a user's stated preference, rule, feedback, or fact in LiMem, a long-term memory system for future coding sessions.

In plain words
What is it for?
Use it when a user explicitly asks the assistant to remember something or strongly corrects how work should be done.
Why use it?
It prevents important preferences from being forgotten between sessions, while distinguishing lasting rules from context-dependent memories.

Skill for Claude Code

Written for Claude Code: arguments in frontmatter. Also seen: mentions CLAUDE.md; positional $N argument; mentions Claude Code.

Part of the limem plugin — 13 skills shipped together

Good fit Use it when a user explicitly asks the assistant to remember something or strongly corrects how work should be done.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gaooooosh/limem-agent-plugin/limem.remember
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 gaooooosh/limem-agent-plugin --skill limem.remember
Clone the repo
git clone --depth 1 https://github.com/gaooooosh/limem-agent-plugin

Made for: Claude Code.

Or install limem, the plugin that ships this one along with the rest of its 13 skills.

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 limem.remember

README.md
[![agentmods](https://agentmods.dev/badge/skills/gaooooosh/limem-agent-plugin/limem.remember/github.svg)](https://agentmods.dev/skills/gaooooosh/limem-agent-plugin/limem.remember)
Your own site
<a href="https://agentmods.dev/skills/gaooooosh/limem-agent-plugin/limem.remember"><img src="https://agentmods.dev/badge/skills/gaooooosh/limem-agent-plugin/limem.remember/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 limem.remember

Your own site · 80×15
<a href="https://agentmods.dev/skills/gaooooosh/limem-agent-plugin/limem.remember"><img src="https://agentmods.dev/badge/skills/gaooooosh/limem-agent-plugin/limem.remember.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 125 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,671 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 $0.00125 $0.01671
Opus 5.5 $0.00050 $0.00668
Sonnet 5.5 $0.00025 $0.00334
Haiku 4.5 $0.00013 $0.00167

Measured 2mo ago against content hash a1fb4e2a9ecb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

limem.remember 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 2mo 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.

plugin-src/skills/limem.remember/SKILL.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/limem.remember — 把用户陈述固化为长期记忆(event 写入 + mention 抽取)

何时调用

  • 用户显式说 "remember X" / "以后这个项目不要 Y" / "always Z" / "记住 W"
  • 用户对刚才输出强烈纠正("不对,应该…"),此时主动建议保存为 feedback
  • 用户在 Claude Code 输入 /limem.remember <text> 或 Codex 输入 $limem.remember <text> 时

边界(v3)

本 skill 只写 event:

  • event:进入 BM25 软召回池,summary 由后端 LLM 抽取,importance 由 mem_type 决定。
  • mentions(旧字段名 entities):抽取的 canonical / aliases 进入 BM25 tag-token 与本地 raw_metadata.canonicals,召回时增强匹配;不再注册为后端 entity。
  • principal_ids:根据 scope / mem_type 自动推断本次 event 应挂的 principals (user / agent / project),写入本地 metadata,soft 召回时降权过滤。

本 skill 不写 principal 的 markdown 档案。要附长文档(用法 / 反例 / 约定)请用 /limem.pattern project|user|agent——这是 v3 的设计分工。

LiMem 现在按上下文相关性召回,canonical / aliases 会作为 trigger 辅助命中;它不再适合保存"必须每轮生效"的无条件约束。始终生效的要求应写入 CLAUDE.md、AGENTS.md 或全局系统指令。

处理步骤(严格按顺序)

Step 1 — 解析输入与 mention 抽取

把 $1 / $ARGUMENTS 当成"用户原话"。从中抽出关键 mentions(每个抽这些字段):

  • canonical:mention 的规范名(如 npm run dev、docker rebuild、react-query、/api/v2)
  • role:在规则中扮演的角色:
    • forbidden — 被禁止 / 不允许的事
    • preferred — 被推荐 / 应该用的事
    • subject — 规则关心的主题但本身不禁不推(如"前端"、"数据库迁移")
    • neutral — 纯 fact 类引用
  • aliases(可选,建议 2–6 个):跨工具家族、跨语言、口语 / 正式形态的同义说法。 这些进入 BM25 tag-token 与本地 metadata 镜像,是匹配口语化 prompt 的关键。
  • description(可选):一句话描述该 mention 在本规则下的含义(≤ 60 字符),仅落本地 metadata 不上行后端。

抽取要点:

  1. 单条 remember 通常 1–3 个 mention;不要无中生有。
  2. canonical 必须是用户原话或一对一可还原的规范化;不要意译。
  3. aliases 给跨工具家族(npm/yarn/pnpm/bun)、跨语言(中文/英文)、口语 / 正式形态。
  4. 不要枚举大量触发短语——长文档与"档案级"约定走 /limem.pattern。

Few-shot 范例

例 1:"以后这个项目不要用 npm run dev,直接 docker rebuild"

{
  "text": "以后这个项目不要用 npm run dev,直接 docker rebuild",
  "scope": "project",
  "mem_type": "rule",
  "importance": 0.9,
  "entities": [
    {
      "canonical": "npm run dev",
      "role": "forbidden",
      "aliases": ["npm dev", "yarn dev", "pnpm dev", "bun dev", "起一下 dev"]
    },
    {
      "canonical": "docker rebuild",
      "role": "preferred",
      "aliases": ["docker compose up --build", "重建 docker", "重新构建容器"]
    }
  ]
}

Read the full file on GitHub · 139 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. 2mo ago First seen · 139 lines · 125 tokens per session scan A a1fb4e2a9ecb

Subscribe to this mod's changes

limem.remember is a skill published in the GitHub repository gaooooosh/limem-agent-plugin (2 stars, last pushed 5mo ago), licensed MIT. It adds 125 tokens to every session and 1,671 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

limem.remember compared with skills from other repositories

limem.remember next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
limem.remembergaooooosh/limem-agent-pluginSkill25mo agoMITA125Claude Code
knowledge-ingestopenclaw/openclawSkill394ktodayMITA80Claude Code, Codex
mem0-oss-to-platformmem0ai/mem0Skill69kyesterdayApache-2.0A217Claude Code, Codex
forgetasgeirtj/system_prompts_leaksSkill71kyesterdayCC0-1.0A0Claude Code, Codex
Cortexdanielmiessler/LifeOSSkill20k2d agoMITA184Claude Code
ha-data-storesshiwenwen/hope-agentSkill1.9ktodayMITA115Claude Code, Codex
memoryopensquilla/opensquillaSkill7.1k7d agoApache-2.0A44Claude Code, Codex