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 metago-ai/metagolifeform --skill metago-thought-11-reality-drivengit clone --depth 1 https://github.com/metago-ai/metagolifeformWrote 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/metago-ai/metagolifeform/metago-thought-11-reality-driven)<a href="https://agentmods.dev/skills/metago-ai/metagolifeform/metago-thought-11-reality-driven"><img src="https://agentmods.dev/badge/skills/metago-ai/metagolifeform/metago-thought-11-reality-driven/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/metago-ai/metagolifeform/metago-thought-11-reality-driven"><img src="https://agentmods.dev/badge/skills/metago-ai/metagolifeform/metago-thought-11-reality-driven.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 | $0.00054 | $0.00895 |
| Opus 5 | $0.00027 | $0.00447 |
| Sonnet 5 | $0.00011 | $0.00179 |
| Haiku 4.5 | $0.00005 | $0.00089 |
Grade A, and why
metago-thought-11-reality-driven 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.
What it actually says
现实驱动智能论 V26.0
描述
以"世界模型"为核心的智能体决策理论，通过评估智能体对现实世界的建模质量与决策驱动机制，量化系统的"现实驱动度"，指导智能体的感知-决策闭环设计。
触发条件
- 评估智能体的现实感知与决策能力
- 设计智能体的世界模型
- 评估决策是否基于现实而非幻觉
- 智能体架构选型
前置条件
- 明确的智能体系统
- 可观测的感知-决策链路
元思想核心
现实驱动核心命题：
智能 = 世界模型质量 * 决策驱动度
世界模型四要素：
WM = (Perception + Representation + Prediction + Grounding) / 4
| 要素 | 含义 | 评估 |
|---|---|---|
| Perception | 对现实世界的感知精度 | 传感器/数据源的丰富度与准确度 |
| Representation | 内部表征的保真度 | 内部模型与现实的映射精度 |
| Prediction | 对未来状态的预测能力 | 预测准确率与时间窗口 |
| Grounding | 符号与现实的锚定 | 抽象概念是否有现实对应 |
决策驱动度：
DD = Decision_Grounded_in_WM / Total_Decisions
- DD = 1：所有决策都基于世界模型
- DD < 0.5：超过一半的决策脱离现实（幻觉风险）
现实驱动度：
R = WM * DD
- R >= 0.7：强现实驱动
- 0.4 <= R < 0.7：部分现实驱动
- R < 0.4：幻觉驱动（高风险）
推理框架
步骤 1：世界模型评估
- Perception：感知源的覆盖度与精度
- Representation：内部表征与现实的差异
- Prediction：预测能力与准确率
- Grounding：抽象概念的锚定程度
步骤 2：决策驱动度评估
- 抽样决策，检查是否基于世界模型
- 计算幻觉决策比例
- 评估 DD 值
步骤 3：现实驱动度计算
- R = WM * DD
- 判定驱动等级
步骤 4：感知-决策闭环分析
- 感知->表征->预测->决策->执行->反馈->更新
- 识别闭环中的断裂点
步骤 5：优化策略
- 若 Perception 低：增加感知源、提升数据质量
- 若 Representation 低：改进模型架构、增加训练
- 若 Prediction 低：增强时序建模、因果推理
- 若 Grounding 低：增加符号锚定、实体链接
- 若 DD 低：强制决策基于世界模型输出
验证方法
- 世界模型四要素是否有可量化的评估方法
- DD 的抽样是否有代表性
- R 值计算是否正确
- 感知-决策闭环是否有断裂点识别
- 幻觉决策是否有具体案例佐证
- 用对抗测试验证：注入虚假感知，系统是否如预测般产生幻觉决策
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 · 97 lines · 54 tokens per session scan A 5eecbbdc5c52
metago-thought-11-reality-driven is a skill published in the GitHub repository metago-ai/metagolifeform (4 stars, last pushed 11d ago), licensed MIT. It adds 54 tokens to every session and 895 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 2026-09-03.
Other skills, from other repositories
embed
Generate, inspect, and use node/text embeddings in Semantica — compute Node2Vec embeddings, find similar nodes, score link predictions, batch similarity, and pairwise similarity. Uses NodeEmbedder, SimilarityCalculator, LinkPredictor, and AgentContext. Sub-commands: compute, similar, similarity, predict-link…
visualize
Visualize the Semantica knowledge graph — topology, centrality, communities, paths, embeddings, decision insights, and temporal evolution. Uses GraphAnalyzer, CentralityCalculator, CommunityDetector, PathFinder, and ContextGraph analytics. Sub-commands: topology, centrality, community, path, decision-graph, insights…
reason
Run reasoning over the Semantica knowledge graph — deductive logic, abductive hypothesis generation, Datalog programs, SPARQL queries, Rete network evaluation. Uses DeductiveReasoner, AbductiveReasoner, DatalogReasoner, SPARQLReasoner, ReteEngine. Sub-commands: deductive, abductive, datalog, sparql, rete, prove…
temporal
Temporal graph operations on Semantica — scoped queries at a point in time, graph snapshots, node change timelines, temporal causal analysis, and graph state reconstruction. Uses AgentContext.findprecedents(asof=), ContextGraph.stateat(), CausalChainAnalyzer.traceattime(), and TemporalQueryRewriter. Sub-commands…
validate
Validate Semantica pipelines, extraction quality, graph schemas, and ontology consistency. Returns structured error/warning checklists. Uses PipelineValidator, PipelineBuilder.validatepipeline(), GraphValidator, and OntologyValidator. Sub-commands: pipeline, step, dependencies, extraction, graph, ontology, performance.
extract
Run the full Semantica semantic extraction pipeline on a file or selected text — NER, relations, events, coreference resolution, triplets, and validation. Clears result cache before each run. Returns Markdown tables with entity/relation/event/triplet results and inline validator warnings.