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.
curl -O https://raw.githubusercontent.com/wlsdks/ontology-atlas/main/.agents/skills/ontology-extract/SKILL.mdgit clone --depth 1 https://github.com/wlsdks/ontology-atlasWrote 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/wlsdks/ontology-atlas/ontology-extract)<a href="https://agentmods.dev/skills/wlsdks/ontology-atlas/ontology-extract"><img src="https://agentmods.dev/badge/skills/wlsdks/ontology-atlas/ontology-extract/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/wlsdks/ontology-atlas/ontology-extract"><img src="https://agentmods.dev/badge/skills/wlsdks/ontology-atlas/ontology-extract.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 58 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 73 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00037 | $0.01068 |
| Opus 5 | $0.00018 | $0.00534 |
| Sonnet 5 | $0.00007 | $0.00214 |
| Haiku 4.5 | $0.00004 | $0.00107 |
Grade A, and why
ontology-extract 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.
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Extract ontology from prose
/ontology-sync follows code changes. This skill follows human prose: meeting
notes, RFCs, pull-request descriptions, chat logs, or pasted wiki paragraphs.
The vault is the Markdown folder whose files and typed frontmatter form the graph.
Run when
- the user explicitly asks to turn supplied prose into ontology;
- the user requests extraction from an RFC, meeting note, PR, wiki, or chat that states a codebase concept.
Pasted prose alone is not an extraction request; follow the requested task.
Skip personal notes without domain/capability/element concepts, summary-only requests, and prose already living inside the target vault node.
1. Read prose and the existing vault together
list_kinds
find_evidence(title)
query_ontology({ operation: "similar_nodes", candidateSlug, title })
Extract candidate nouns and verb phrases, then search before proposing. The most
common failure is creating “user login” beside an existing auth-login node.
A similarity score at or above 0.3 is a prompt to consider patching the existing
node; lower scores support a new candidate but do not decide it automatically.
2. Classify a small candidate set
One paragraph normally yields zero to three candidates. More than five means the input is too broad or the extraction is too eager.
| Prose shape | Likely kind | Example |
|---|---|---|
| a new user ability | capability |
“members can reset a password” → capabilities/password-reset |
| a library, file, runtime unit, or implementation role | element |
“send an OTP” → elements/otp-sender |
| a stable responsibility area | domain |
“separate billing” → domains/billing |
| opinion, status, or motivation only | skip | do not turn commentary into a node |
For each candidate record slug, title, parent domain where relevant, the exact source phrase, and whether it is new or a patch candidate.
3. Stop before writing
Reuse an explicit approval already given in this session only when the exact candidate content, relations, source evidence, and conditions are unchanged. A general request to extract meaning is not approval of unseen candidates. If no existing explicit approval covers the exact current candidates, show one short numbered table and ask the user to choose. Otherwise, proceed to step 4 without asking again. With zero candidates, report that result without requesting approval or writing anything:
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.
- 6d ago Changed · +8 lines 533f2155abbd
- 12d ago First seen · 114 lines · 37 tokens per session scan A 33c65428f2ec
ontology-extract is a skill published in the GitHub repository wlsdks/ontology-atlas (104 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 1,068 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 2026-08-30.
Other skills, from other repositories
memtrace-decision-memory
Use Cortex decision memory through the normal Memtrace MCP tools. Trigger for free-text questions about what was decided, chosen, rejected, banned, or established as a convention; for why a symbol exists or which contracts constrain it; for whether a known decision held, drifted, or was violated; and for the…
memtrace-index
Index a source-code repo into the Memtrace knowledge graph and poll the job to completion. Use when the user asks to index, parse, ingest, reindex, watch, or prepare a source-code repo for Memtrace analysis, when code exploration needs an index, or when searches return 0/partial results for source paths under an…
memtrace-session-continuity
Catch up on everything that changed in an indexed source-code repo since the last session, using stored session anchors and Memtrace change memory. Use when the user asks to continue, catch up, resume, see what changed while away, recover prior context, or orient at session start without guessing timestamps. Do not…
memtrace-continuous-memory
Keep the Memtrace index fresh while editing by watching a repo for live, incremental re-indexing. Use when the user asks to keep Memtrace fresh while editing, watch a repo, enable live or incremental indexing, set up always-on memory (meaning Memtrace index watching, not generic agent memory), or make just-saved…
repo-docs-intelligence-bootstrap
Use when a repository needs one lightweight repository memory profile that evolves with the codebase to reduce drift, prevent structural mistakes, and keep current repository truth plus durable working context explicit. Trigger for requests to refresh current-state or architecture docs from live code, classify or…
llm-wiki-bootstrap
Use this skill when the user wants to scaffold a new Obsidian-first LLM Wiki workspace, bootstrap Andrej Karpathy-style LLM Wiki structure, create raw/wiki/AGENTS.md layout in a fresh project, or standardize a markdown-first knowledge vault with scripts, templates, and meta pages. Trigger on requests to set up an LLM…