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 TashanGKD/cognitive-os --skill cognitive-creative-synthesisgit clone --depth 1 https://github.com/TashanGKD/cognitive-osWrote 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/tashangkd/cognitive-os/cognitive-creative-synthesis)<a href="https://agentmods.dev/skills/tashangkd/cognitive-os/cognitive-creative-synthesis"><img src="https://agentmods.dev/badge/skills/tashangkd/cognitive-os/cognitive-creative-synthesis/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/tashangkd/cognitive-os/cognitive-creative-synthesis"><img src="https://agentmods.dev/badge/skills/tashangkd/cognitive-os/cognitive-creative-synthesis.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 | $0.00110 | $0.02040 |
| Opus 5 | $0.00055 | $0.01020 |
| Sonnet 5 | $0.00022 | $0.00408 |
| Haiku 4.5 | $0.00011 | $0.00204 |
Grade A, and why
cognitive-creative-synthesis 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 12d 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cognitive-creative-synthesis(创造性发散 / DMN+CEN协同等效)
对应认知活动:高创造力状态——DMN(自由联想)与 CEN(目标维持)协同激活,产生远距联想(Remote Associates)
认知五维坐标(COG-TAX):
- 意识程度:显性(用户主动参与,选择有价值的方向)
- 脑网络:DMN(发散/联想)+ CEN(目标约束/收敛)协同
- 记忆系统:语义记忆(L1)跨维度的随机激活
- 执行功能:转换(在不同概念框架之间切换)
- 双系统:系统1(快速联想生成)→ 系统2(用户评估筛选)
理论依据:Mednick (1962) 远距联想理论;Beaty et al. (2016) 高创造力者 DMN-CEN 协同;Wallas (1926) 顿悟四阶段(酝酿→豁朗)
⚠️ 特别设计说明:本 Skill 刻意在发散阶段豁免 P1「验证优先」约束——创造性阶段的价值在于暂时松开验证要求,先生成所有可能性,再由用户系统2筛选。收敛时恢复正常验证流程。
知识导航表
| 层级 | 文档 | 用途 |
|---|---|---|
| D0 认知地图 | cognitive/L0_brain_map.md |
获取当前认知体系的六个维度及其L1文档列表(用于随机抽样) |
激活后立即执行
Step 1 接收当前问题
从用户消息中提取:
- 当前面对的问题/任务(是什么)
- 已经尝试过的方案(选填,若用户有提到)
- 遇到的具体障碍(「卡在哪里了」)
输出确认:「理解了。当前问题:[一句话总结]。现在开始跨领域发散。」
Step 1.5 前置条件检查(安全退出点)
Read: cognitive/L0_brain_map.md
IF 文件不存在:
→ 告知用户:
「认知体系地图(L0_brain_map.md)尚未建立,无法执行跨领域结构类比发散。
建议先运行 cognitive-reorganize 建立认知体系,再使用本Skill。」
→ 退出,不继续执行
IF 文件存在 → 继续 Step 2
Step 2 读取认知体系维度地图
Read: cognitive/L0_brain_map.md
→ 提取:当前认知体系包含哪些维度(例:产品理论/认知科学/组织设计/研究范式/...)
→ 去除与当前问题「表面最相关」的1-2个维度(刻意避开直接相关领域)
→ 从剩余维度中随机选取 2-3 个「表面不相关」的维度
Step 3 从选定维度随机提取概念
对每个选定维度:
Read: 该维度对应的 L1 文档(选取1份;若维度有多份L1,随机选1份)
→ 读取文档的核心概念/章节标题(前三个主要概念,不读全文)
→ 随机选取1个概念,作为「类比源」
Step 4 强制寻找结构相似性(核心步骤,不允许说「没有关联」)
对每个「类比源概念」,必须完成以下推导:
问题1:「[类比源概念X] 的核心工作机制是什么?」(一句话,聚焦结构而非表象)
问题2:「这个机制:[X的机制] 和当前问题「[Y]」有没有相同的底层结构?」
问题3:「如果把这个结构类比应用到 [Y],暗示的非常规解法是什么?」
⚠️ 执行铁律:
- 必须完成所有3个问题,即使联系很牵强
- 禁止说「这个概念和当前问题没有关联」(强制找结构相似)
- 质量不重要,覆盖率更重要——先生成全部可能性,再筛选
Step 5 输出候选方案列表(不筛选,不评价,全部呈现)
格式:
---
**来自[维度名]的类比:[类比源概念]**
[类比源]的工作机制:[一句话]
结构相似点:[为什么这个机制和当前问题有相同的底层结构]
暗示的非常规解法:[基于这个类比,对当前问题「[Y]」的一个不常规解法]
---
(对每个类比源重复以上格式)
Step 6【γ】 等待用户筛选(决策权归用户)
输出:
「以上是基于跨领域结构类比生成的候选方向([N]个)。
哪个方向值得深入探索?
[A: 深入方向1] [B: 深入方向2] [C: 深入方向3]
[D: 这些都没用,再来一批不同的]
[E: 回到原来的思路]」
等待用户选择后:
→ 若选某方向:「好的,基于[选定方向]的类比,进一步展开:...」
→ 若选「再来一批」:重新执行 Step 2-5(换一批维度)
→ 若选「回到原来」:结束本Skill,不输出任何内容
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.
- 12d ago First seen · 150 lines · 110 tokens per session scan A fb24079d0ad9
cognitive-creative-synthesis is a skill published in the GitHub repository TashanGKD/cognitive-os (9 stars, last pushed 5mo ago), licensed MIT. It adds 110 tokens to every session and 2,040 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.
Other skills, from other repositories
document-pipeline
A writing workflow for producing documents, articles, reports, and papers through research, drafting, fact checking, review, illustration planning, and format conversion.
cognitive-reorganize
A workflow for reorganising scattered documents into a complete personal knowledge structure.
project-backlog
A project backlog manager that stores mixed requests in a project to-do document and can later process them by priority.
project-retrospective
A project review workflow that examines the skills used during a completed project and records improvements for future work.
skill-rule-修改规范
A change procedure for modifying skills, rules, and agents—the files that define how an AI system behaves. It covers backups, review questions, minimal edits, change records, and index updates.
skill-sandbox-expander
A workflow for expanding a library of tested scenario examples, called sandboxes, by finding missing task types, cross-domain cases, edge cases, and variants.