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 kings0527/agent-skills --skill cognitive-runtime-skill-systemgit clone --depth 1 https://github.com/kings0527/agent-skillsWrote 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/kings0527/agent-skills/cognitive-runtime-skill-system)<a href="https://agentmods.dev/skills/kings0527/agent-skills/cognitive-runtime-skill-system"><img src="https://agentmods.dev/badge/skills/kings0527/agent-skills/cognitive-runtime-skill-system/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/kings0527/agent-skills/cognitive-runtime-skill-system"><img src="https://agentmods.dev/badge/skills/kings0527/agent-skills/cognitive-runtime-skill-system.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 | $0.00000 | $0.01679 |
| Opus 5 | $0.00000 | $0.00839 |
| Sonnet 5 | $0.00000 | $0.00336 |
| Haiku 4.5 | $0.00000 | $0.00168 |
Grade A, and why
cognitive-runtime-skill-system 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 9d 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 — 588 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cognitive Runtime Skill System
面向 LLM / Multi-Agent 的贝叶斯认知运行时架构
0. 核心目标
不是:
- 提升语言流畅度
- 增加 prompt 长度
- 堆叠 agent 数量
而是:
重塑 LLM 的认知动力学(Cognitive Dynamics)
目标:
- 延缓错误收敛
- 维持不确定性
- 提高信息增益
- 降低 hallucination
- 提高长期更新能力
- 防止群体认知塌缩
1. 核心思想
普通 Prompt Engineering:
输入 → 输出
高级 Cognitive Runtime:
Belief State
↓
Hypothesis Competition
↓
Evidence Update
↓
Constraint Filtering
↓
Adversarial Verification
↓
Posterior Revision
↓
Action / Reflection
本质:
把 LLM 从“语言补全器”
变成“概率认知系统”
2. Runtime 总架构
User Query
↓
Context Parser
↓
Constraint Extractor
↓
Hypothesis Generator
↓
Belief State Manager
↓
Evidence Evaluator
↓
Adversarial Layer
↓
Bayesian Update Layer
↓
Decision Layer
↓
Output Synthesizer
3. 核心 Runtime Modules
3.1 Belief State Manager(核心)
职责:
维护:
- 当前信念状态
- confidence
- uncertainty
- competing hypotheses
- dependency graph
数据结构
belief_state:
hypotheses:
- id: H1
confidence: 0.52
uncertainty: 0.21
- id: H2
confidence: 0.31
uncertainty: 0.44
核心原则
不允许单一确定性状态。
必须:
- 多假设并存
- 动态竞争
- 持续更新
3.2 Hypothesis Generator
职责:
强制生成:
- 多路径解释
- 多方案推理
- 多层级分析
禁止
直接给唯一答案
必须
hypotheses:
- ...
- ...
- ...
原因
LLM 最大问题:
early convergence(过早收敛)
3.3 Constraint Extractor
优先提取:
- 时间约束
- 风险约束
- 算力约束
- 信息约束
- 激励约束
- 法律约束
- 现实可执行性
原则
不允许脱离约束纯推理
因为:
理论最优 ≠ 现实最优
3.4 Evidence Evaluator
职责:
分析:
- 证据质量
- 来源可靠性
- 独立性
- 时间衰减
- 信息增益
Evidence Object
evidence:
source: ...
reliability: 0.82
independence: 0.71
timestamp: ...
关键问题
LLM 极易:
把重复信息误判为独立证据。
3.5 Adversarial Layer(极关键)
职责:
主动寻找:
- 反例
- 边界条件
- 极端情况
- 推理漏洞
- posterior collapse
强制问题
什么证据最可能推翻当前结论?
原因
默认 LLM:
天然偏向自洽。
而不是:
主动证伪。
3.6 Bayesian Update Layer
核心:
0
但:
现实实现重点不是公式。
而是:
- evidence weighting
- uncertainty maintenance
- update throttling
- anti-collapse
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.
- 9d ago First seen · 588 lines · 0 tokens per session scan A 749a9e3890de
cognitive-runtime-skill-system is a skill published in the GitHub repository kings0527/agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,679 tokens. 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…