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 wpsnote/wpsnote-skills --skill ie-retrieve-memorygit clone --depth 1 https://github.com/wpsnote/wpsnote-skillsWrote 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/wpsnote/wpsnote-skills/ie-retrieve-memory)<a href="https://agentmods.dev/skills/wpsnote/wpsnote-skills/ie-retrieve-memory"><img src="https://agentmods.dev/badge/skills/wpsnote/wpsnote-skills/ie-retrieve-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/wpsnote/wpsnote-skills/ie-retrieve-memory"><img src="https://agentmods.dev/badge/skills/wpsnote/wpsnote-skills/ie-retrieve-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 | $0.00119 | $0.01126 |
| Opus 5.5 | $0.00048 | $0.00450 |
| Sonnet 5.5 | $0.00024 | $0.00225 |
| Haiku 4.5 | $0.00012 | $0.00113 |
Grade A, and why
ie-retrieve-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.
What it actually says
记忆层:历史知识检索
本技能负责从用户的 WPS 笔记库中检索与当前上下文相关的历史知识。 这是灵感引擎(Inspiration Engine)三层架构中的最底层,为上层推理和洞见提供原始素材。
适用场景
当用户需要找回过去的笔记内容时使用,典型场景包括:
- 用户在写新笔记时想知道过去是否写过类似主题
- 用户想回顾某个项目或主题的历史记录
- 被 ie-engine 编排器调用,作为灵感生成流水线的第一步
- 用户明确要求"找找以前的笔记"或"回忆之前的想法"
不适用场景
以下场景不应使用此技能(避免误触发):
- 搜索代码文件或项目文件(使用文件搜索工具)
- 查找网页内容(使用浏览器工具)
- 创建或编辑笔记内容(使用 wpsnote 工具直接操作)
- 通用的知识问答(直接回答即可)
检索策略
根据用户提供的线索,选择合适的检索方式组合。检索的目标是"宁多勿少",因为后续推理层会负责筛选和聚类。
1. 关键词检索
当用户提供了明确的主题或关键词时优先使用。
步骤:
- 从用户的描述中提取核心关键词(2-5 个)
- 使用 wpsnote 的 search_notes 工具按关键词检索
- 对命中的笔记,使用 get_note_outline 获取结构概览
2. 标签检索
当用户提到的主题可能对应已有标签时使用。
步骤:
- 使用 find_tags 查找相关标签
- 使用 search_notes 按标签筛选笔记
- 多标签时取并集,扩大召回范围
3. 时间维度检索
当用户提到时间线索时使用,例如"去年写的""上个月的笔记"。
步骤:
- 根据用户描述推断时间范围
- 使用 list_notes 按时间排序和筛选
- 结合关键词进一步过滤
4. 笔记内容深入检索
当初步检索结果不够精确时,对候选笔记进行内容级搜索。
步骤:
- 对候选笔记使用 search_note_content 搜索具体内容
- 使用 read_blocks 读取匹配段落的上下文
- 必要时使用 read_section 读取完整章节
输出格式
检索完成后,按以下结构整理结果。这个格式设计为可以直接传递给推理层(ie-connect-dots)使用。
检索结果摘要
---
检索条件:[使用的关键词/标签/时间范围]
命中笔记数:[数量]
---
笔记 1
标题:[笔记标题]
笔记ID:[note_id]
创建时间:[时间]
标签:[标签列表]
核心内容摘要:[与检索主题相关的关键段落摘要,100-200字]
笔记 2
标题:[笔记标题]
...
---
检索置信度:高/中/低
补充说明:[如果检索范围可能不完整,说明原因和建议]
检索数量控制
- 默认返回最相关的 5-10 条笔记
- 如果用户明确要求"尽量多找",可以扩大到 20 条
- 如果是被 ie-engine 编排器调用,按编排器的指示控制数量
- 每条笔记的摘要控制在 200 字以内,避免信息过载
与其他灵感引擎技能的关系
本技能是灵感引擎的 记忆层,在三层架构中处于最底层:
ie-generate-insight(洞见层)<-- 消费推理结果
ie-connect-dots(推理层) <-- 消费检索结果
ie-retrieve-memory(记忆层)<-- 本技能,提供原始素材
- 上游:无(本技能是流水线起点)
- 下游:ie-connect-dots(推理层)接收本技能的检索结果
- 编排:ie-engine 负责串联调用
本技能可以独立使用(用户只想找回旧笔记),也可以作为灵感引擎流水线的一部分。
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 · 126 lines · 119 tokens per session scan A f6d415dfbfce
ie-retrieve-memory is a skill published in the GitHub repository wpsnote/wpsnote-skills (183 stars, last pushed yesterday), licensed MIT. It adds 119 tokens to every session and 1,126 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 2026-08-30.
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…
remem
Use when the user asks Codex to recall prior project context, save durable decisions or bug fixes, inspect remem memory health, or activate remem automatic memory hooks from the Codex plugin.
evo-memory-review
Review and curate an evo-subagent role's prefercmd.md and memory.md using evidence from actual runs. Use when evolution entries are stale, duplicated, contradictory, or too noisy.
ai-memory-coding-conventions
Project coding conventions extracted from chat history. Load when writing new code, naming things, designing APIs, or reviewing PRs. Topics: Cursor pagination is mandatory for all paged GraphQL endpoints.
ai-memory-decision-log
Technical decisions made for this project, with reasoning and rejected alternatives. Load when proposing architectural changes, evaluating alternatives, or asked why a choice was made. Topics: Adopt OAuth 2.0 authorization code flow with PKCE for the customer portal SPA.
ai-memory-system-architecture
System architecture facts: components, data flow, integration boundaries. Load when implementing cross-component features, debugging integration issues, or onboarding to the codebase. Topics: Event sourcing for the billing audit log.