cognitive-consistency-check

cognitive-consistency-check is a skill for Cursor from TashanGKD/cognitive-os. It costs 67 tokens per session (5,052 once invoked), scanned A, original, MIT.

A full validation of a structured knowledge system against ten consistency rules, including existing references, declared relationships, document status, and non-contradictory content.

In plain words
What is it for?
Use it to scan the knowledge files, report violations, and repair inconsistencies according to the system’s maintenance rules.
Why use it?
It finds broken links, missing files, stale status information, incomplete indexes, and other structural problems that can make the system unreliable.

Skill for Cursor

Written for Cursor: installed under .cursor/.

Good fit Use it to scan the knowledge files, report violations, and repair inconsistencies according to the system’s maintenance rules.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/tashangkd/cognitive-os/cognitive-consistency-check"><img src="https://agentmods.dev/badge/skills/tashangkd/cognitive-os/cognitive-consistency-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,052 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 $0.00067 $0.05052
Opus 5 $0.00034 $0.02526
Sonnet 5 $0.00013 $0.01010
Haiku 4.5 $0.00007 $0.00505

Measured 10d ago against content hash 5c52d47732e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

cognitive-consistency-check 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-consistency-check/SKILL.md · 359 lines

How it starts

The opening of the file, as written. The whole thing — 359 lines — stays where its author put it; the contents beside it link to each section on GitHub.

一致性验证 Skill(Cognitive Consistency Check)

基于 维护协议_自洽规范.md 的C1-C10条件,对认知结构做完整验证。 发现问题后立即修复,不允许「知道有问题但先放着」。


知识导航表(执行前必须理解的概念根)

层级 文档 需要理解的概念
D0 认知根(必读) cognitive/L1_knowledge/系统架构思维维度/自进化智能体系统形式规范_v1.0.md 层3:C2关系显式化(对象间依赖必须声明);层4:RelType(structural/uses/invokes/verifies/mentions)
D3 规范参考 cognitive/maintenance_protocol.md C1~C10完整一致性条件(本 Skill 的执行依据)
D4 运行时数据 所有L1文档 + L1.5底层原则库.md 被验证的K-objects(需要全量扫描)

核心概念速查: ① 一致性 = R中所有对象的关系(C2)都能成立;对象的当前状态符合其依赖关系 ② C1~C10分别对应不同类型的一致性:版本一致/引用存在/内容非矛盾等 ③ 发现不一致后立即修复(ceremony(K)),不留挂起状态


激活后立即执行

Step 1  读取 认知结构/维护协议_自洽规范.md
        → 确认当前有效的C1-C10条件
        → 确认版本控制要求(0.2条)

Step 2  枚举认知结构的实际文件状态
        → 列出 L1_系统性文档/ 所有.md文件(排除历史版本和变更记录)
        → 列出 L2_碎片化思考/ 所有.md文件(排除碎片整合索引)
        → 检查 L0_大脑总地图.md 是否存在且包含框架图

C1:L0完备性

验证:L0大脑总地图中列出的所有文档,在认知结构目录中实际存在
方法:读取L0中的文档路径列表,用Glob逐一确认文件存在
结果:✅/⚠️(列出具体缺失文件)

C2:L0时效性

验证:L0中每篇文档的状态(✅/◑/❌)是否反映实际情况
方法:对比L0状态标注与实际文件的最后修改时间
结果:✅/⚠️(列出状态过时的条目)

C2+:L0框架图(铁律)

验证:L0必须包含可视化框架图(见维护协议0.1条)
方法:搜索L0中是否包含ASCII框图(包含╔═╗等字符 或 ┌─┐等字符)
结果:✅/❌(没有框架图 = 严重违规,必须立即补充)

C3:知识图谱完整性

验证:知识图谱_正式文档.md中的节点数 = 认知结构L1目录中的文档数
方法:
  → 枚举 L1_系统性文档/ 实际文档数量
  → 统计知识图谱中登记的L1节点数量
  → 两者应相等
结果:✅/⚠️(列出图谱中缺少的文档)

C4:碎片索引完整性

验证:碎片整合索引覆盖所有L2文档
方法:
  → 枚举 L2_碎片化思考/ 所有实际.md文件(排除索引本身)
  → 检查每个文件是否在索引中有对应条目
结果:✅/⚠️(列出索引缺失的L2文档)

C5:分类清单准确性

验证:文档分类清单中已迁入的文档状态为★,未迁入的为◑
方法:
  → 读取文档分类清单
  → 对每个★条目,确认认知结构中实际有该文档
  → 对每个◑条目,确认认知结构中确实没有该文档
结果:✅/⚠️(列出状态不准确的条目)

【执行控制补丁(缺口B修复,2026-03-25)】【α】(以下补录操作 AI 直接执行,无需用户确认)
认知科学依据:元认知监控→执行控制迁移(Flavell 1979 + Miyake et al. 2000 执行功能)
——检测到缺口后必须立即启动修复,而非只报告。当前C5停留在「监控」层,缺少「修复启动」组件。

IF 发现已在L1目录中存在但清单状态为◑或未登记的文档:
  → 立即批量执行补录(不需要用户确认,因为这是客观事实而非主观判断)
  → 在文档分类清单末尾追加条目:
    | [文件完整路径] | [文档类型:L1/REF-EXT] | [归属维度] | ★ CURRENT | [简要描述] |
  → 补录完成后报告:「已补录 N 个未登记文档 → ✅ C5 已修复」
IF 发现清单中★但文件不存在:
  → 报告给用户,不自动修改(删除条目需要确认)

C6:DUPLICATE标注完整性

Read the full file on GitHub · 359 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 · 359 lines · 67 tokens per session scan A 5c52d47732e4

Subscribe to this mod's changes

cognitive-consistency-check is a skill published in the GitHub repository TashanGKD/cognitive-os (9 stars, last pushed 5mo ago), licensed MIT. It adds 67 tokens to every session and 5,052 once invoked, about $0.0003 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.