cognitive-background-synthesizer

cognitive-background-synthesizer is a skill for Cursor from TashanGKD/cognitive-os. It costs 103 tokens per session (2,148 once invoked), scanned A, original, MIT.

A background process that looks for connections between recent notes and completed tasks, then writes possible patterns into a system log.

In plain words
What is it for?
Use it for periodic cross-topic analysis of recent fragments and work records, producing synthesis reports for a later daily briefing.
Why use it?
It can surface relationships between ideas captured at different times without requiring the user to review everything manually.

Skill for Cursor

Written for Cursor: installed under .cursor/.

Good fit Use it for periodic cross-topic analysis of recent fragments and work records, producing synthesis reports for a later daily briefing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tashangkd/cognitive-os/cognitive-background-synthesizer
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-background-synthesizer
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-background-synthesizer

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/tashangkd/cognitive-os/cognitive-background-synthesizer"><img src="https://agentmods.dev/badge/skills/tashangkd/cognitive-os/cognitive-background-synthesizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,148 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 $0.00103 $0.02148
Opus 5 $0.00051 $0.01074
Sonnet 5 $0.00021 $0.00430
Haiku 4.5 $0.00010 $0.00215

Measured 11d ago against content hash 8e7c149aa3cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

cognitive-background-synthesizer 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 11d 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-background-synthesizer/SKILL.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cognitive-background-synthesizer(后台认知合成 / DMN等效)

对应认知活动:默认模式网络(DMN)——大脑空闲时自发做的跨话题后台合成、远距联想、洞见生成。人类的很多「灵光一闪」发生在非专注状态,这个Skill模拟这个过程。

认知五维坐标(COG-TAX)

  • 意识程度:隐性(用户不参与,后台自动)
  • 脑网络:DMN(默认模式网络,后台合成主导)
  • 记忆系统:情节记忆(L2/L3)跨时间的模式提取
  • 执行功能:无(自动化关联分析)
  • 双系统:系统1(自动模式匹配)→ 结果供用户用系统2评估

理论依据:Buckner et al. (2008) DMN综述;Christoff et al. (2016) 心智游走与创造性思维;Kounios & Beeman (2014) 顿悟神经机制

调用方式:后台脚本,每3天执行一次(headless模式) 人工触发(可选):「执行后台合成」「cognitive-background-synthesizer」


知识导航表

层级 文档 用途
D0 碎片索引 cognitive/L2_fragments/fragment_index.md 获取最近14天新增碎片的ID和标题
D0 任务日志 cognitive/L3_logs/task_log.md 获取最近14天任务摘要(「完成的工作」字段)
D0 知识图谱 cognitive/knowledge_graph.md 了解L1文档间关系(判断同话题簇)

激活后立即执行(Headless 模式)

Step 0  输入充分性检查(安全退出点)
        Read: cognitive/L2_fragments/fragment_index.md
        → 统计最近14天内「待整合」碎片数量
        → 若 < 3条 → 静默退出,在系统日志写一行「条件未满足:碎片不足3条,跳过」
        → 若 ≥ 3条 → 继续

Step 1  读取输入材料
        Read: cognitive/L2_fragments/fragment_index.md
        → 提取最近14天新增的「待整合」碎片:{碎片ID, 标题, 关键词, capture_date, 归属维度}

        Read: cognitive/L3_logs/task_log.md
        → 提取最近14天的任务记录,仅读「完成的工作」字段(每条取前200字)
        → 若任务日志过大(>50条),只取最近20条

        Read: cognitive/knowledge_graph.md(若存在)
        → 获取L1文档节点列表和主要关系边
        → 若文件不存在:跳过图谱参考,仅基于碎片关键词做分析

Step 2  跨碎片关联分析(核心步骤)
        对 Step 1 收集到的全部碎片内容,寻找以下三类模式:

        模式A:「相同底层结构」
          条件:两个或多个碎片,讨论了不同现象,但底层逻辑相同
          判断方法:碎片的核心动词/因果关系是否高度相似?
          输出:「碎片[A] 和碎片[B] 都在说:[共同底层结构,一句话]」

        模式B:「碎片解释任务困难」
          条件:某个碎片的核心洞见,可以解释任务日志中提到的某个困难/失败
          判断方法:碎片关键词与任务摘要中的「问题/困难/没想到」部分是否高度相关?
          输出:「任务「[任务名]」遇到的困难,可能与碎片「[碎片标题]」的洞见有关」

        模式C:「候选重复/合并」
          条件:相隔 > 7天捕捉的两个碎片,实质上在说同一件事
          判断方法:碎片标题/核心词高度重叠(>60%语义相似)
          输出:「碎片[A]([日期A])与碎片[B]([日期B])实质相同,建议合并」

Step 3  生成合成报告
        Write: cognitive/L3_logs/synthesis_report_YYYYMMDD.md(新建)
        格式:
        ---
        ## 后台合成报告(YYYY-MM-DD)
        
        ### 发现的跨碎片连接(模式A)
        [若无发现:「本次未发现跨碎片连接」]
        - 连接1:碎片「[A标题]」× 碎片「[B标题]」
          共同底层结构:[一句话]
          建议行动:[整合到同一L1章节 / 提炼为新原则候选 / 暂时观察]
        
        ### 碎片-任务关联(模式B)
        [若无发现:「本次未发现碎片-任务关联」]
        - 任务「[任务名]」中的困难 → 可能与碎片「[碎片标题]」相关
          关联说明:[一句话]
        
        ### 候选重复/合并建议(模式C)
        [若无发现:「本次未发现候选重复」]
        - 碎片「[A]」([日期])≈ 碎片「[B]」([日期]),建议合并处理
        ---

Step 4  追加到待完成清单
        Write: cognitive/L3_logs/todo.md(追加)
        □ [synth-YYYYMMDD] 后台合成报告已生成,建议查看
          路径:cognitive/L3_logs/synthesis_report_YYYYMMDD.md
          发现:[连接X条,关联Y条,重复Z条]

Step 5  追加系统日志
        Write: cognitive/L3_logs/system_log.md(追加)
        格式:[LOG-YYYYMMDD-NN] cognitive-background-synthesizer | 合成完成:发现连接X条,关联Y条,重复Z条 | synthesis_report_YYYYMMDD.md

Read the full file on GitHub · 152 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. 11d ago First seen · 152 lines · 103 tokens per session scan A 8e7c149aa3cf

Subscribe to this mod's changes

cognitive-background-synthesizer is a skill published in the GitHub repository TashanGKD/cognitive-os (9 stars, last pushed 5mo ago), licensed MIT. It adds 103 tokens to every session and 2,148 once invoked, about $0.0005 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.