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 Vladick-Pick/business-ontology --skill build-braingit clone --depth 1 https://github.com/Vladick-Pick/business-ontologyWrote 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/vladick-pick/business-ontology/build-brain)<a href="https://agentmods.dev/skills/vladick-pick/business-ontology/build-brain"><img src="https://agentmods.dev/badge/skills/vladick-pick/business-ontology/build-brain/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/vladick-pick/business-ontology/build-brain"><img src="https://agentmods.dev/badge/skills/vladick-pick/business-ontology/build-brain.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 | $0.00035 | $0.03083 |
| Opus 5 | $0.00017 | $0.01541 |
| Sonnet 5 | $0.00007 | $0.00617 |
| Haiku 4.5 | $0.00003 | $0.00308 |
Grade A, and why
build-brain 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 11d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build brain
Purpose
The accepted Markdown/Git export is the current compile input. The target operational source of truth is the canonical model store; until that service exists, the accepted export is the reviewed, portable model surface the registry compiler reads. A consumer — a dashboard interpreter, a financial overlay, the OpenClaw agent in team chat, an MCP server — cannot ask "what does the attraction module produce?" or "what is the impact radius if this interface changes?" against prose. It needs a graph: typed nodes and edges keyed by stable id.
Build brain runs scripts/build_registry.py to compile the accepted cards into nodes.json, edges.json, and manifest.json, then checks integrity. This is the step that turns "agent-queryable" from a promise into a fact. You run it so the model can be traversed, not just read.
Why it matters that this is a compile, not authoring: the registry is derived. Nobody edits it by hand. If the graph and the accepted export disagree, fix the accepted model/export sync and recompile — never patch the JSON. A hand-edited registry is a second, silently-drifting truth surface, which is exactly the failure this kit exists to prevent.
When to use
Run build brain when any of these is true:
- A card was just promoted from
staged/to accepted (the model grew). - Links were added, removed, or rewired between cards.
- You are about to hand the model to a consumer (dashboard, MCP, agent, overlay) and need a current, valid graph.
- The cadence sweep promoted reviewed cards and you want the registry to reflect them.
- The user asks to "build/rebuild the brain", "recompile the registry", "rebuild the graph", or "validate the links".
This skill is self-initiated: after a promotion lands, you don't wait to be asked — you recompile and show the result, because a stale registry is worse than no registry (it answers queries with old reality).
Do not run it as part of authoring or while cards are still staged. Staged cards are proposals, not committed reality; compiling them would let an unapproved proposal answer queries as if it were true.
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.
- 11d ago First seen · 146 lines · 35 tokens per session scan A 4e0e61c64527
build-brain is a skill published in the GitHub repository Vladick-Pick/business-ontology (2 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 3,083 once invoked, about $0.0002 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…
objectstack-ai
Design ObjectStack AI skills, tools, knowledge sources, and the open-edition MCP server surface. Use when the user is adding .skill.ts / .tool.ts, configuring an LLM provider, wiring the tools a skill grants, or indexing ObjectStack data as a knowledge source for RAG. Agents themselves are platform-internal (ask /…
prepare-data
Profile and prepare raw source files before modeling or loading them into Cruxible; validate keys, grain, joins, and transformation needs, then produce a concrete readiness report.
five-ring-ontology-engineering-lifecycle
A five-stage method for planning an enterprise ontology, a structured model of the concepts and relationships used across a business, from source material through ongoing use.
ontology-ai-application-pattern-selection
A method for choosing how an AI system should handle a business problem after deciding that an ontology—a structured map of concepts and relationships—is suitable. It compares patterns such as workflow automation, decision support, knowledge answering, collaboration, and continuous planning.