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 Square-Q/subconscious-skill --skill subconsciousgit clone --depth 1 https://github.com/Square-Q/subconscious-skillWrote 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/square-q/subconscious-skill/subconscious)<a href="https://agentmods.dev/skills/square-q/subconscious-skill/subconscious"><img src="https://agentmods.dev/badge/skills/square-q/subconscious-skill/subconscious/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/square-q/subconscious-skill/subconscious"><img src="https://agentmods.dev/badge/skills/square-q/subconscious-skill/subconscious.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.02546 |
| Opus 5.5 | $0.00000 | $0.01018 |
| Sonnet 5.5 | $0.00000 | $0.00509 |
| Haiku 4.5 | $0.00000 | $0.00255 |
Grade A, and why
subconscious 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 — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Subconscious Agent Skill
概述
本 Skill 赋予 Claude Code 意识/潜意识/前意识三重结构,仿生人类认知架构。
它不是"带记忆的助手",而是带活潜意识的 Agent——潜意识层在后台持续处理联想、模式识别、记忆重整,通过 whisper 机制在适当时机影响意识层的决策。
核心架构
意识层 (Conscious) ← 当前会话的主推理流程
├─ 接收用户指令、写代码、工具调用
├─ 直接查询前意识层(知识库/文档)
└─ 接收潜意识 whisper 注入
前意识层 (Preconscious) ← 静态知识仓库
├─ 代码库索引 / 项目文档
├─ 外部数据库 / API 文档
└─ 意识层按需直接检索
潜意识层 (Subconscious) ← 后台持续处理引擎
├─ 跨会话模式识别
├─ 记忆联想(当前→历史关联)
├─ 凝缩/压缩同类记忆
├─ 重要性加权与遗忘
├─ 梦境处理(空闲期重放+重整)
└─ 输出:whisper 消息(不写用户文件,不阻塞主流程)
触发机制
自动激活
以下条件激活潜意识层:
- 会话开始 → 检查预注入包,如有则生成 whisper
- 会话进行中 → 以下场景触发即时联想:
- 检测到当前问题和某段历史记忆的模式高度匹配
- 用户重复踩同类型的坑
- 出现已记录的重要概念/符号
- 会话结束 → 执行潜意识处理管道(编码→联想→凝缩→固化→预注入)
- 空闲定时 → 梦境处理 + 遗忘扫描
手动命令
直接操控潜意识层:
| 命令 | 效果 |
|---|---|
/subconscious status |
查看潜意识状态、记忆统计 |
/subconscious recall <关键词> |
强行召回关联记忆 |
/subconscious dream |
触发一次梦境处理 |
/subconscious forget <条件> |
显式标记某记忆可遗忘 |
/subconscious pin <记忆ID> |
固定某条记忆防止衰减 |
/subconscious off |
关闭潜意识层(当前会话) |
/subconscious whisper |
查看当前预注入包内容 |
潜意识处理管道
每一段会话结束后,按顺序执行以下五阶段:
Stage 1: 编码 (Encoding)
- 读取当前会话的 transcript(或记录的关键事件)
- 提取:决策点、问题、新知识、重复模式
- 每条提取内容附重要性评分(0.0–1.0)
- 输出:结构化记忆片段列表
Stage 2: 联想 (Association)
- 对新记忆片段做语义匹配,关联已有历史记忆
- 建立关联图:因果链、相似度、对比关系
- 输出:记忆关联关系表
Stage 3: 凝缩 (Condensation)
- 聚类同类事件(相同领域、相似问题、重复模式)
- 聚类数 ≥ 3 的记忆群 → 压缩为一个抽象 insight
- 细节丢弃规则:保留共性,舍弃个案特例
- 输出:凝缩后的记忆 + 被压缩的冗余标记
Stage 4: 固化 (Consolidation)
- 将处理后的记忆写入三种记忆类型
- 更新记忆索引
- 调整重要性分数:当前引用的 +0.1,未被引用的 -5%(衰减)
- 低于阈值 0.1 的 → 归档(不删除)
- 输出:记忆存储确认 + 索引变更日志
Stage 5: 预注入 (Pre-inject)
- 选择与当前项目/语境最高相关度的记忆片段
- 打包为 whisper 消息(≤3 条,每条 ≤80 字)
- 存至预注入缓冲区,下次会话开始读取
- 输出:预注入包
记忆系统
三种记忆类型
情景记忆 (Episodic)
- 内容:具体会话事件、决策上下文
- 结构:
{time, project, context, key_decision, outcome, importance} - 用于:回忆特定场景、追溯决策原因
语义记忆 (Semantic)
- 内容:抽象知识、概念定义、技术规则
- 结构:
{concept, domain, definition, related_semantic_ids, source_episodic_ids} - 用于:知识问答、概念关联、方案推理
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 · 237 lines · 0 tokens per session scan A 6dea1787b53c
subconscious is a skill published in the GitHub repository Square-Q/subconscious-skill (48 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,546 tokens. 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
knowledge-ingest
Ingest documents, articles, conversations, or supplied text into Knowledge with retained originals, sourced claims, entity updates, timelines, and cross-links; also learn durable lessons from a set of conversations, transcripts, or past sessions (/learn), including the Learn from conversations and Learn from Memory…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…