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 SuperChason/ontology-driven-ai-data-management-skills --skill intent-driven-minimal-ontology-loadinggit clone --depth 1 https://github.com/SuperChason/ontology-driven-ai-data-management-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/superchason/ontology-driven-ai-data-management-skills/intent-driven-minimal-ontology-loading)<a href="https://agentmods.dev/skills/superchason/ontology-driven-ai-data-management-skills/intent-driven-minimal-ontology-loading"><img src="https://agentmods.dev/badge/skills/superchason/ontology-driven-ai-data-management-skills/intent-driven-minimal-ontology-loading/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/superchason/ontology-driven-ai-data-management-skills/intent-driven-minimal-ontology-loading"><img src="https://agentmods.dev/badge/skills/superchason/ontology-driven-ai-data-management-skills/intent-driven-minimal-ontology-loading.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 | $0.00086 | $0.01410 |
| Opus 5 | $0.00043 | $0.00705 |
| Sonnet 5 | $0.00017 | $0.00282 |
| Haiku 4.5 | $0.00009 | $0.00141 |
Grade A, and why
intent-driven-minimal-ontology-loading 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 4d 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
意图驱动的最小本体检索与加载
方法骨架
- 根据当前用户意图只加载完成决策所需的最小本体、事实和工具。
- 先把目标拆成边界清晰、互不重叠、可独立执行的意图。
- 再将意图映射到子本体、事实时间窗、规则和Action能力。
- 规则清晰、低容错任务优先图查询；模糊表达可先向量召回再图精查。
- 加载范围随风险、上下文和任务进展渐进扩展，避免全量上下文冲突。
- 输出应记录意图、加载版本、检索依据和未加载原因。
触发场景
用户会在什么情境下需要这个 Skill
- Agent上下文过长或本体加载过多
- 同一问法可能对应不同业务意图
- 需要设计子本体路由和图向量混合检索
语言信号
- “只加载当前需要的本体”
- “这个意图该路由到哪个子本体”
- “图检索和向量检索怎么组合”
- 英文信号：minimal ontology, intent routing, hybrid retrieval
与相邻 Skill 的区分
- 与
ontology-constraint-and-knowledge-injection：本 skill 决定取哪些知识；知识注入策略决定怎样把知识交给模型。 - 与
fact-reason-goal-explainable-decision：本 skill 负责运行时上下文选择；事实事理目标负责在上下文内完成决策。
执行步骤
按当前任务选择必要步骤；已有可靠成果直接复用：
-
解析意图
- 动作：提取对象、目标、时间、范围、风险和期望输出，识别歧义。
- 完成标准：意图可执行且不与其他子意图重叠；歧义已澄清。
-
建立路由
- 动作：映射到最小子本体、事实源、规则集、Action和版本。
- 完成标准：每项资源都能说明与当前决策的必要关系。
-
选择检索
- 动作：规则明确时图精查；表达模糊时向量召回后图校验；需要历史经验时补充记忆。
- 完成标准：检索策略与风险、清晰度和时效相匹配。
-
控制加载
- 动作：设置Token预算、时间窗、层级深度和渐进扩展条件。
- 完成标准：上下文只包含必要知识，冲突和过期版本已排除。
-
记录与校验
- 动作：输出意图、资源、版本、查询、证据和未加载项，运行关键约束检查。
- 完成标准：相同输入可复现加载结果，高风险缺项触发人工介入。
固定输出
- 意图定义表：意图编号、原始表达、对象、目标、时间、范围、风险、期望输出和歧义状态
- 子意图拆分与依赖表
- 意图—资源路由表：子本体、事实源、时间窗、规则集、Action、版本、必要性证据和未加载原因
- 检索策略表：图精查、向量召回、历史记忆或组合策略及校验方式
- 加载边界与预算表：Token、时间窗、关系深度、资源数、停止条件和渐进扩展条件
- 加载结果与约束检查记录：实际资源、版本、查询、证据、冲突、过期项和检查结果
- 高风险缺失、人工介入与重现信息清单
相同输入应能重现意图、路由、版本和加载结果；意图未澄清或关键资源缺失时保留受阻状态。
使用边界
不要在以下情况使用
- 意图尚未澄清却直接静默路由
- 任务需要全域审计或全局一致性检查
- 只在离线阶段设计知识资产分类
常见失败模式
- 用全量模型重构适配企业业务：企业知识被压入模型参数，适配成本从局部语义治理升级为模型训练、维护和全量数据治理。
- 一次性加载全量本体和超长上下文：有限上下文被低相关知识占据，关键规则的有效权重下降，冲突信息增加概率性选择空间。
- 任务边界和本体粒度失配：建模单元没有绑定具体Agent任务及评价标准，模型边界与执行边界无法对齐。
使用折扣与复核要求
- 最小加载可能漏掉未知关联，应为高风险任务设置扩展检索和人工复核。
- 大模型生成形式结构无法直接证明业务语义正确，生产使用需保留专家确认、工具校验、真实用例和审计记录。
相关 Skills
depends-on→fact-reason-action-business-loop。
审计信息
- 历史验证：v0.1.0 路由测试 6/6；v0.4.0 已通过输出契约结构校验，跨平台行为继续按版本抽样
- 首次公开版本：2026-08-21
- 来源说明：方法框架受《本体驱动的 AI 数据管理》启发；仓库不包含原书正文。
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago Changed 78d6bd006750
- 8d ago Changed · +7 lines 5d364e2fc703
- 12d ago First seen · 98 lines · 86 tokens per session scan A f7213e63ff63
intent-driven-minimal-ontology-loading is a skill published in the GitHub repository SuperChason/ontology-driven-ai-data-management-skills (10 stars, last pushed 5d ago), licensed MIT. It adds 86 tokens to every session and 1,410 once invoked, about $0.0004 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
open-ontologies
AI-native ontology engineering using 50+ MCP tools backed by an in-memory Oxigraph triple store. Build, validate, query, and govern RDF/OWL ontologies with a generate-validate-iterate loop. Use when building ontologies, knowledge graphs, RDF data, SPARQL queries, BORO/4D modeling, SHACL validation, clinical…
mykg
Run mykg knowledge-graph commands inside Claude Code from one slash command /mykg. The user describes intent in natural language (extract, append, sync, resume, approve, walkthrough, parse-docs, fetch-web, query); the skill parses intent, builds the right mykg CLI command from the live --help output, confirms, runs…
ontology-ontology-architect
Design a domain ontology from evidence using layered modeling, stable concept definitions, explicit relations, SKOS-first structure, and selective OWL formalization with recorded modeling decisions.
graphify
Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community…
graph-mutation-plan
Cookbook for composing an applygraphmutations plan — stable entitykey patterns, the canonical label/edge vocabulary, evidence/invalidation/confidence discipline, and a worked example. Load this when building a non-trivial mutation plan.
understand-knowledge
Analyze a Karpathy-pattern LLM wiki knowledge base and generate an interactive knowledge graph with entity extraction, implicit relationships, and topic clustering.