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 propose-changegit 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/propose-change)<a href="https://agentmods.dev/skills/vladick-pick/business-ontology/propose-change"><img src="https://agentmods.dev/badge/skills/vladick-pick/business-ontology/propose-change/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/propose-change"><img src="https://agentmods.dev/badge/skills/vladick-pick/business-ontology/propose-change.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 | $0.00028 | $0.03261 |
| Opus 5 | $0.00014 | $0.01631 |
| Sonnet 5 | $0.00006 | $0.00652 |
| Haiku 4.5 | $0.00003 | $0.00326 |
Grade A, and why
propose-change 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Propose change
This is the agent's single authored write path into the business ontology. Everything the agent wants to add or correct goes through here as a staged proposal, written only under staged/, for an authorized human to review. The deterministic controller applies the exact approved revision.
Purpose
The model of reality is shared between humans and agents, and it is only trustworthy if a human stands behind every accepted fact. So the system splits authority by construction: the agent proposes, the human decides, and a non-generative controller applies. This skill is the agent half of that split.
The reason it is a separate write path is that the proposal/decision gate must be enforced by capabilities, not good intentions. An agent that writes straight to accepted cards has self-approved. Staged payloads remain off-limits to accepted queries until an authenticated human decision and deterministic controller application.
The second reason is legibility. A good proposal is not "here is the new text." It is a diff (what was → what is now), the basis, where that basis came from, how confident the agent is, and which skill produced it. That turns review from re-deriving the agent's reasoning into checking a claim. Cheap review is what keeps a human in the loop without the human becoming the bottleneck.
When to use
Use this whenever the agent is about to record anything into the model:
- It mined a new term, artifact, metric, business, production system, interface, process, state, or decision from a source and wants it captured.
- It noticed an existing card is wrong, stale, or under-defined and wants to correct it.
- It found a new link between existing cards (one of the closed ten relations).
- It saw the model diverge from reality in conversation and wants to log the drift or gap.
- A human said "add that to the ontology" / "capture this" / "that contradicts what we have."
Do not use it for:
- Pure discussion where nothing is being recorded yet — talk first, propose once a claim firms up.
- Promoting a card or editing anything under the promoted tree (
modules/,interfaces/,decisions/, the numbered files, etc.). The generative agent has no accepted-write authority; the deterministic controller applies only a reviewed package. - Running queries or reads against the model — that is not a write and needs no proposal.
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 · 196 lines · 28 tokens per session scan A daef1cf6ade3
propose-change is a skill published in the GitHub repository Vladick-Pick/business-ontology (2 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 3,261 once invoked, about $0.0001 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
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.
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…
Rare Disease Skills Index
Skills for rare disease case support: ontology-first normalization/retrieval and the clinical genetics consult report format contract (structure + theme). Load the relevant skill file when performing the matching task.
objectstack-platform
Bootstrap, configure, extend, and operate ObjectStack runtimes. Covers project setup (defineStack, drivers, scaffolding), declaring platform capabilities (requires: — which service plugins boot), plugin and service development (PluginContext, DI, kernel hooks like kernel:ready), and operations (CLI commands…
objectstack-automation
Design ObjectStack automation — Flows (visual logic), Triggers, Approvals, state machines, and the jobs (defineJob) / webhooks (defineWebhook) stack collections. Use when the user is adding .flow.ts, wiring an event-driven rule, modelling an approval chain, or building an interactive screen flow / wizard…
objectstack-data
Design ObjectStack data schemas — objects, fields, field conditional rules, relationships, validations, indexes, lifecycle hooks, permissions, row-level security, data lifecycle retention/TTL/rotation, metadata protection locks, and external / federated datasources (defineDatasource) — and the seeds (defineSeed())…