cognitive-consolidate

cognitive-consolidate is a skill for Cursor from TashanGKD/cognitive-os. It costs 107 tokens per session (1,993 once invoked), scanned A, original, MIT.

A scheduled memory-maintenance skill that groups older notes and incorporates them into broader knowledge documents.

In plain words
What is it for?
Use it as a background process every seven days, or trigger it manually, to consolidate at least three notes that have been waiting for seven days.
Why use it?
It prevents mature notes from remaining scattered and records conflicting items for a person to decide.

Skill for Cursor

Written for Cursor: installed under .cursor/.

Good fit Use it as a background process every seven days, or trigger it manually, to consolidate at least three notes that have been waiting for seven days.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/tashangkd/cognitive-os/cognitive-consolidate"><img src="https://agentmods.dev/badge/skills/tashangkd/cognitive-os/cognitive-consolidate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 107 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,993 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 $0.00107 $0.01993
Opus 5 $0.00053 $0.00996
Sonnet 5 $0.00021 $0.00399
Haiku 4.5 $0.00011 $0.00199

Measured 11d ago against content hash 3a6e236d769e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

cognitive-consolidate 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-consolidate/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cognitive-consolidate(记忆巩固 / 睡眠期巩固等效)

对应认知活动:睡眠期记忆巩固(海马体→皮层长期存储)——定期将积压的L2碎片批量整合进L1,完成情节记忆→语义记忆的转化

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(离线加工,记忆重激活)
  • 记忆系统:情节记忆→语义记忆的转化(海马体→皮层)
  • 执行功能:无(自动化批处理)
  • 双系统:系统1(自动批处理,不需要有意识的决策)

理论依据:Stickgold (2005) 睡眠依赖性记忆巩固;Wilson & McNaughton (1994) 海马体重激活;McClelland et al. (1995) 互补学习系统理论

调用方式:后台脚本,每7天执行一次(headless模式) 人工触发(可选):「执行记忆巩固」「批量整合积压碎片」


知识导航表

层级 文档 用途
D0 碎片索引 cognitive/L2_fragments/fragment_index.md 找到所有「待整合且已成熟」的碎片
D0 L1 目标 cognitive/L1_knowledge/[各维度文档] 整合的目标文档
D0 L0 地图 cognitive/L0_brain_map.md 了解文档间依赖关系

激活后立即执行(Headless 模式,所有决策使用默认策略)

Step 0  成熟度检查(安全退出点)
        Read: cognitive/L2_fragments/fragment_index.md
        → 筛选条件:状态=🔲待整合 AND capture_time < 今天-7天
        → 若成熟碎片 < 3条 → 静默退出(输出「巩固条件未满足,退出」到系统日志后结束)
        → 若 ≥ 3条 → 继续 Step 1

Step 1  读取成熟碎片
        对每个成熟碎片 ID:
        Read: cognitive/L2_fragments/[对应碎片文件]
        → 提取:碎片标题、核心内容、归属维度、capture_time、归因类型

Step 2  按关联 L1 分组
        根据碎片的「归属维度」字段,将碎片分组:
        组1: 归属 [维度A] 的碎片 → 目标 L1 文档 = [维度A对应文档]
        组2: 归属 [维度B] 的碎片 → 目标 L1 文档 = [维度B对应文档]
        ...
        若碎片无明确归属维度 → 归入「待分类」组,追加到待完成清单(不自动处理)

Step 3  逐组执行整合(supplement路径优先,conflict路径不自动执行)
        对每个分组:
        Read: cognitive/L1_knowledge/[目标文档] 全文
        
        对每个碎片,判断整合路径:
        
        supplement(补充)路径 ← 默认执行:
          条件:碎片内容与L1现有内容兼容,可直接添加
          动作:在L1文档对应章节末尾追加碎片内容(StrReplace)
                追加格式:「— (来自L2碎片 [碎片ID],[capture_date])」
        
        conflict(冲突)路径 ← 不自动执行,转入人工决策:
          条件:碎片内容与L1现有核心论点存在实质矛盾
          动作:追加到待完成清单(Step 4),不修改L1
        
        covered(已覆盖)路径 ← 静默归档:
          条件:碎片内容已被L1现有内容完整覆盖
          动作:更新碎片状态为「📦已归档(被L1覆盖)」

Step 4  conflict 类碎片追加到待完成清单
        Write: cognitive/L3_logs/todo.md(追加)
        格式:
        □ [巩固-YYYYMMDD] 碎片[ID]「[标题]」与[L1文档名]存在冲突,需人工决策
          碎片内容摘要:[前100字]
          冲突点:[一句话描述]

Step 5  更新碎片整合索引
        Write: cognitive/L2_fragments/fragment_index.md
        → 已supplement碎片:状态改为「✅已整合(巩固批次 YYYYMMDD)」
        → 已covered碎片:状态改为「📦已归档」
        → conflict碎片:状态改为「⏸️冲突待决策」

Step 6  写入巩固报告
        Write: cognitive/L3_logs/consolidation_report_YYYYMMDD.md(新建)
        内容:
        ---
        ## 记忆巩固报告(YYYY-MM-DD)
        - 处理碎片总数:N条
        - supplement(已整合):X条 → [列出碎片ID和目标文档]
        - covered(已归档):Y条
        - conflict(待人工决策):Z条 → [列出碎片ID]
        - 静默退出原因:无(或:成熟碎片不足3条)
        ---

Step 7  追加系统日志
        Write: cognitive/L3_logs/system_log.md(追加)
        格式:[LOG-YYYYMMDD-NN] cognitive-consolidate | 巩固完成:整合X条,归档Y条,冲突Z条待决策 | fragment_index.md

Read the full file on GitHub · 143 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 · 143 lines · 107 tokens per session scan A 3a6e236d769e

Subscribe to this mod's changes

cognitive-consolidate is a skill published in the GitHub repository TashanGKD/cognitive-os (9 stars, last pushed 5mo ago), licensed MIT. It adds 107 tokens to every session and 1,993 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.