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/gaooooosh/limem-agent-plugin/limem.patternnpx skills add gaooooosh/limem-agent-plugin --skill limem.patterngit clone --depth 1 https://github.com/gaooooosh/limem-agent-pluginWhat 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 | $0.00110 | $0.01402 |
| Opus 5 | $0.00055 | $0.00701 |
| Sonnet 5 | $0.00022 | $0.00280 |
| Haiku 4.5 | $0.00011 | $0.00140 |
Grade A, and why
limem.pattern 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 2d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/limem.pattern — Principal Markdown 档案的唯一编辑入口
每个 principal(user / agent / project / team / service)可以挂一篇 markdown 文档。
后端按 ^## 切片,每段独立打分;客户端在 UserPromptSubmit 时按相关性注入命中段。
/limem.remember 只写 event,不会自动生成档案——档案必须通过本 skill 显式编辑。
文档结构完全自由,建议(但不强制)用 H2 分节:
## 命令规约/## Commands(项目偏好/禁用的开发命令)## 用法/## How to use## 反例/## Don't## 风格/## Style(代码风格、注释语言、命名)## 相关/## See also
何时调用
- 用户说 "给项目写个档案" / "把约定记下来" / "update my agent profile"
- 用户问 "limem 里关于本项目存了什么" / "show me my user profile"
- 自动建议:在
/limem.remember完成后、scope=project 且 mem_type=rule 累计较多时, 主动建议把规约 append 到 project principal
参数解析
$1= principal 标识:- 别名:
project/user/agent(最常用;自动解析到当前会话的 stable id) - 或完整
entity_id(形如principal_project_<sha8>/principal_user_<sha8>/principal_agent_<slug>)
- 别名:
$2=mode:get/put/append,缺省getget—— 拉取并展示当前 markdown,不写后端put—— 整篇覆盖(需要用户确认;新内容从交互式提示读取多行)append—— 内部先get,把新增段落拼到末尾再put;适合"加一节规约"
处理步骤
Step 1 — 解析 principal
直接把 $1 传给 limem_pattern_get / put / delete 即可——这些工具内部已经支持
project / user / agent 别名解析。如果输入是用户编造的别名(如某个 canonical 字符串),
工具会在 entity 不存在时返回错误,按 Step 3 处理。
Step 2a — mode=get
调 limem_pattern_get(entity_id="<alias_or_id>"),渲染:
📄 Principal <entity_id> 的当前档案(共 <total_chars> 字符):
<content(原样 markdown,不要二次格式化)>
如需修改:再次运行 /limem.pattern <alias> put
如需追加章节:/limem.pattern <alias> append
若 has_pattern=false → 提示"该 principal 尚无档案",给出 put 模板示例。
Step 2b — mode=put
-
先
limem_pattern_get拉旧版本作为对照(若有)。 -
强制确认 UI(覆盖语义不可逆——后端无版本历史):
⚠️ 即将整篇覆盖 principal <entity_id> 的档案。 旧版本字符数:<old_total_chars> 新版本字符数:<new_total_chars> 旧档案前 5 行 / 新档案前 5 行 对照... 确认覆盖?[y / n] -
用户
y→ 调limem_pattern_put(entity_id, content);其它 → "已取消"。 -
回执:
✓ principal <entity_id> 档案已 <created|updated>(总字符 <total_chars>)。 下次 SessionStart 与匹配 prompt 时会自动召回 H2 切片。
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.
- 2d ago First seen · 120 lines · 110 tokens per session scan A 4417a5053aeb
limem.pattern is a skill published in the GitHub repository gaooooosh/limem-agent-plugin (2 stars, last pushed 3mo ago), licensed MIT. It adds 110 tokens to every session and 1,402 once invoked, about $0.0006 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.