ontology-atlas: Skill for Claude Code

.agents/skills/ontology-field-trial/SKILL.md

ontology-field-trial is a skill for Claude Code, Codex from wlsdks/ontology-atlas. It costs 70 tokens per session (4,362 once invoked), scanned A, original, MIT.

A field test for an ontology vault: a structured store of concepts and relationships about a codebase. It gives the vault to another agent without the original source code to see whether the stored information can answer questions on its own.

In plain words
What is it for?
Use it to evaluate changes to ontology construction, Atlas's MCP read/write contract, bootstrap instructions, and the quality of answers produced from the vault alone.
Why use it?
It measures whether the vault contains useful, trustworthy meaning rather than merely a large map of files. Testing an unfamiliar repository reduces the chance of relying on prior knowledge.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is wlsdks/ontology-atlas's own configuration. It tells Claude Code and Codex how to work on ontology-atlas itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ontology-atlas configures →

Reuse

Borrowing it

Nothing to install: this file belongs to wlsdks/ontology-atlas. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/wlsdks/ontology-atlas/main/.agents/skills/ontology-field-trial/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/wlsdks/ontology-atlas

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for ontology-field-trial

README.md
[![agentmods](https://agentmods.dev/badge/skills/wlsdks/ontology-atlas/ontology-field-trial/github.svg)](https://agentmods.dev/skills/wlsdks/ontology-atlas/ontology-field-trial)
Your own site
<a href="https://agentmods.dev/skills/wlsdks/ontology-atlas/ontology-field-trial"><img src="https://agentmods.dev/badge/skills/wlsdks/ontology-atlas/ontology-field-trial/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.

agentmods 80×15 button for ontology-field-trial

Your own site · 80×15
<a href="https://agentmods.dev/skills/wlsdks/ontology-atlas/ontology-field-trial"><img src="https://agentmods.dev/badge/skills/wlsdks/ontology-atlas/ontology-field-trial.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,362 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00070 $0.04362
Opus 5 $0.00035 $0.02181
Sonnet 5 $0.00014 $0.00872
Haiku 4.5 $0.00007 $0.00436

Measured 6d ago against content hash 7e0152cbd560, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ontology-field-trial 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 6d 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.

.agents/skills/ontology-field-trial/SKILL.md · 365 lines

How it starts

The opening of the file, as written. The whole thing — 365 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Field trial — does the vault survive being the only thing you have?

This project sells a meaning layer that an agent consumes. The only test of that claim is to take the source away and see whether the vault still answers. Everything else — node counts, green checks, a map that looks full — measures effort, not usefulness.

Use the Atlas meta-model specification as the shared answer key for kind, relation, direct is_a, and unsupported inference claims. The trial measures whether agents can apply that contract; it must not invent a second rubric from the vault it is judging.

Run this as four measurements, in order. Each one produces a number or a list that goes in the report. Do not skip a phase because the previous one looked good — phase 1 has looked good every time, and phases 2–4 are where the defects were.

Before you start

Pick a repository nobody in this session knows, permissively licensed (Apache-2.0 / MIT / BSD), in a domain you cannot bluff. That is the point: a familiar repository lets the agent — and you — fill gaps from memory, and the whole trial then measures your memory instead of the vault.

⚠️ Never name the chosen repository in this repo's code, tests, identifiers, fixtures, or commit messages (.claude/rules/forbidden.md — no third-party brands in identifiers). Everything the trial produces lives outside this checkout — a scratch directory, never inside ontology-atlas/.

# outside this repo
mkdir -p ~/scratch/atlas-field-trial && cd ~/scratch/atlas-field-trial
git clone --depth 1 <repo-url> repo
mkdir vault handoff
node <atlas>/cli/src/index.mjs init vault     # starter nodes only

Before starting the clock or a fresh agent, prepare that agent's exact MCP binding. A session opened in the Atlas checkout may inherit the dogfood server even when the scratch vault has its own config. For source-checkout scratch runs, use the bootstrap skill's rooted MCP reader with absolute server/vault/repository paths. Its automatic connection_info must match both roots before the first census or source read. A mismatch is a setup failure: stop the process, record the elapsed recovery cost, and never call list_kinds, index_project, or a semantic reader on that wrong server. Discover that runner with the resolved script plus the single positional argument schema; --schema, schema --output, and an empty invocation are not rooted-reader discovery forms.

Read the full file on GitHub · 365 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 6d ago Changed · +2 lines · -42 tokens per session 7e0152cbd560
  2. 12d ago First seen · 363 lines · 112 tokens per session scan A e3a01f0da9c1

Subscribe to this mod's changes

ontology-field-trial is a skill published in the GitHub repository wlsdks/ontology-atlas (104 stars, last pushed today), licensed MIT. It adds 70 tokens to every session and 4,362 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 2026-08-30.

Related

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.

potpie-ai/potpie · 51 tokens

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…

fabio-rovai/open-ontologies · 110 tokens

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…

SenolIsci/mykg · 175 tokens

accurate-code

Use when implementing or modifying code with Kontext Brain so each behavior-bearing logic unit is grounded in current provenance-backed decisions, domain terms, invariants, and Evidence.

hj1105/kontext-brain-ts · 36 tokens

container-manager-kg-ingestion

Snapshot a host's Docker/Podman/Swarm inventory into the epistemic-graph knowledge graph as typed OWL nodes via the container-manager-mcp MCP server — containers, images, volumes, networks, swarm services and nodes, with their :usesImage / :runsOn / :builtFrom links. Use when the agent must record live container state…

Knuckles-Team/container-manager-mcp · 116 tokens

action-contract-execution-feedback-loop

A specification method for making a business action into a tool an AI agent can call safely. It defines the action’s inputs, outputs, permissions, preconditions, expected effects, error handling, and audit information.

SuperChason/ontology-driven-ai-data-management-skills · 92 tokens