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-consistency-checkgit 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-consistency-check)<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.
<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>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 | $0.00067 | $0.05052 |
| Opus 5 | $0.00034 | $0.02526 |
| Sonnet 5 | $0.00013 | $0.01010 |
| Haiku 4.5 | $0.00007 | $0.00505 |
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.
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
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.
- 10d ago First seen · 359 lines · 67 tokens per session scan A 5c52d47732e4
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.
Other skills, from other repositories
cognitive-reorganize
A workflow for reorganising scattered documents into a complete personal knowledge structure.
cognitive-ask
A question-answering workflow that answers from a user's own knowledge documents, with sources, confidence levels, contradictions, and gaps made clear.
cognitive-integrate-fragments
A workflow for moving pending thought fragments into broader knowledge documents while preserving the existing structure.
cognitive-capture-fragment
A workflow for capturing brief ideas and storing them as structured entries in a personal knowledge system.
cognitive-extract-principle
A workflow for finding shared patterns across several stored thought fragments and turning them into candidate principles for review.
cognitive-self-reflect
A guided self-reflection process that turns vague observations about your habits or feelings into structured records and compares them with earlier entries.