cognitive-attend

cognitive-attend is a skill for Cursor from TashanGKD/cognitive-os. It costs 121 tokens per session (2,460 once invoked), scanned A, original, MIT.

A signal detector for finding notable ideas in conversation. It looks for insights, connections between topics, contradictions, reflections, and evidence supporting a principle.

In plain words
What is it for?
It scans a selected or recent message, reports the detected signal types, and can route the result to another skill for deeper processing or recording.
Why use it?
It helps prevent useful thoughts hidden in ordinary conversation from being overlooked or lost.

Skill for Cursor

Written for Cursor: installed under .cursor/.

Good fit It scans a selected or recent message, reports the detected signal types, and can route the result to another skill for deeper processing or recording.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tashangkd/cognitive-os/cognitive-attend
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 TashanGKD/cognitive-os --skill cognitive-attend
Clone the repo
git clone --depth 1 https://github.com/TashanGKD/cognitive-os

Made for: Cursor.

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 cognitive-attend

README.md
[![agentmods](https://agentmods.dev/badge/skills/tashangkd/cognitive-os/cognitive-attend/github.svg)](https://agentmods.dev/skills/tashangkd/cognitive-os/cognitive-attend)
Your own site
<a href="https://agentmods.dev/skills/tashangkd/cognitive-os/cognitive-attend"><img src="https://agentmods.dev/badge/skills/tashangkd/cognitive-os/cognitive-attend/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 cognitive-attend

Your own site · 80×15
<a href="https://agentmods.dev/skills/tashangkd/cognitive-os/cognitive-attend"><img src="https://agentmods.dev/badge/skills/tashangkd/cognitive-os/cognitive-attend.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 121 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,460 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 $0.00121 $0.02460
Opus 5 $0.00060 $0.01230
Sonnet 5 $0.00024 $0.00492
Haiku 4.5 $0.00012 $0.00246

Measured 10d ago against content hash d50d2d6777d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

cognitive-attend 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 10d 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.

.cursor/skills/cognitive-attend/SKILL.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cognitive-attend(认知信号检测 / 突显网络 SN 等效)

对应认知活动:突显网络(Salience Network)的信号检测——识别对话内容中「值得深入处理」的认知信号,主动路由给对应的 Skill。

人类大脑在处理日常输入时,SN 负责过滤:哪些信息应该引起注意?哪些需要从「背景」切换到「前景」处理?这个 Skill 模拟这个过程——让你不会遗漏隐藏在普通对话中的重要认知材料。

认知五维坐标(COG-TAX)

  • 意识程度:前意识→显性(自动检测,结果呈现给用户选择)
  • 脑网络:SN(检测不确定性/新颖性/重要性)
  • 记忆系统:无直接写入(信号放大器,不产生独立记录)
  • 执行功能:抑制(阻止忽略重要信号)
  • 双系统:系统1(快速模式匹配)

理论依据:Corbetta & Shulman (2002) 双网络注意模型;Menon & Uddin (2010) SN中枢角色


知识导航表

层级 文档 用途
D0 无需读取外部文档 信号检测基于对话内容,无文档依赖

使用方式

方式一:主动触发(推荐)

用户在任意对话后,说:

  • 「检查一下这段话有没有认知信号」
  • 「有什么值得记录的吗?」
  • 「帮我识别这里的洞见」

AI 执行信号扫描,输出发现的信号。

方式二:作为对话预处理步骤(可选集成)

如果你的系统有对话管理框架(如 session-bootstrap、自定义对话循环等),可以将本 Skill 作为每轮对话的可选预处理步骤:

每轮对话 → [可选] 运行 cognitive-attend 扫描用户消息
         → 若有信号,提示用户选择是否深入处理
         → 用户选择后,触发对应 Skill

集成方法:在你的对话管理系统的"触发词扫描"步骤之后,添加:

IF 用户消息包含以下模式 → 运行 cognitive-attend:
  「我发现/我意识到」+ 规律性表述
  「这跟X一样/和之前的Y很像」
  「但是这里不对/这和之前说的冲突」
  「我又/我总是/我注意到自己」
  「这说明一个规律/这在X里也成立」

激活后立即执行

Step 1  确认扫描对象
        从对话上下文确认要扫描的内容:
        - 若用户明确指定(「检查这段话」「刚才说的」)→ 扫描指定内容
        - 若未指定 → 扫描用户最近一条或两条消息

Step 2  扫描五类显著性信号

        对扫描对象全文做语义分析,逐类检测:

        ─ S1 洞见信号 ────────────────────────────
        模式:「我发现/我意识到/我觉得」+ 原则性/规律性表述
        特征:描述了可以跨情境推广的规律,而不是某次具体的事件
        示例:「我发现每次压力大的时候,我会跳过验证步骤」
        ↓ 若检测到 → 触发建议

        ─ S2 跨域联想信号 ─────────────────────────
        模式:「这跟X一样/和之前的Y很像/让我想到了/这个原理和」
        特征:在不同领域之间发现了结构相似性
        示例:「这个设计方式和我在认知科学里看到的很像」
        ↓ 若检测到 → 触发建议

        ─ S3 矛盾信号 ──────────────────────────────
        模式:「但是这里不对/这和之前说的冲突/这两个是矛盾的」
        特征:识别出两个论述之间的张力或不一致
        示例:「但这和你之前说的「验证优先」好像是冲突的」
        ↓ 若检测到 → 触发建议

        ─ S4 反思信号 ──────────────────────────────
        模式:「我又/我总是/我注意到自己/我有个习惯/我每次都会」
        特征:识别自己行为/思维的反复模式
        示例:「我又在没看完所有信息就下结论了」
        ↓ 若检测到 → 触发建议

        ─ S5 原则印证信号 ──────────────────────────
        模式:「这说明一个规律/这在X里也成立/本质上/根本原因是」
        特征:从具体案例中归纳出抽象规律,且该规律可能跨领域适用
        示例:「这说明一个规律:约束越少,发散越好,但需要一个收敛触发点」
        ↓ 若检测到 → 触发建议

Step 3【α】 输出信号检测结果

        若检测到至少一个信号:
        ---
        🔍 **认知信号检测结果**

        [对每个检测到的信号,输出一段:]

        **[信号类型](S[N])**
        引用片段:「[检测到的原文(10-30字)]」
        信号说明:[一句话解释为什么这是一个[类型]信号]
        建议:[对应操作]
        ---

        若未检测到任何信号:
        → 简短告知:「扫描完成,当前内容中未检测到明显的认知信号。」
        → 不输出空列表,不过度解释

Step 4【γ】 等待用户选择是否处理

        若有信号,在检测结果后输出选项:

        「是否需要现在处理某个信号?
         [处理信号1: 运行 X] [处理信号2: 运行 Y] [全部跳过,稍后再看]」

        → 若用户选择处理某信号 → 触发对应 Skill(cognitive-capture-fragment / cognitive-associate / cognitive-detect-contradiction / cognitive-self-reflect / cognitive-extract-principle)
        → 若用户选择跳过 → 结束,不记录任何内容

Read the full file on GitHub · 193 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. 10d ago First seen · 193 lines · 121 tokens per session scan A d50d2d6777d4

Subscribe to this mod's changes

cognitive-attend is a skill published in the GitHub repository TashanGKD/cognitive-os (8 stars, last pushed 5mo ago), licensed MIT. It adds 121 tokens to every session and 2,460 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.