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 wlsdks/ontology-atlas --skill atlas-absorbgit 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/atlas-absorb)<a href="https://agentmods.dev/skills/wlsdks/ontology-atlas/atlas-absorb"><img src="https://agentmods.dev/badge/skills/wlsdks/ontology-atlas/atlas-absorb/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/atlas-absorb"><img src="https://agentmods.dev/badge/skills/wlsdks/ontology-atlas/atlas-absorb.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00076 | $0.00727 |
| Opus 5 | $0.00038 | $0.00364 |
| Sonnet 5 | $0.00015 | $0.00145 |
| Haiku 4.5 | $0.00008 | $0.00073 |
Grade A, and why
atlas-absorb 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 12d 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
/atlas-absorb — 글을 그래프로
이 스킬의 가장 큰 값은 「안 만드는 것」이다
산문에서 개념을 뽑을 때 가장 흔한 실패는 이미 있는 것을 이름만 바꿔 또 만드는 것이다. 그래서 순서가 「뽑고 나서 중복 확인」이 아니라 「중복 확인하고 나서 뽑기」 다.
- 무엇을 읽나
- 볼트 안(또는 사용자가 가리킨) 파일이면 →
absorb_document({ filePath }).confirm을 빼고 먼저 부른다 — 그러면 쓰지 않고 제안만 돌려준다. - 대화에 붙여 넣은 글이면 → 그 글을 직접 읽고 후보를 뽑는다.
- 후보마다 중복을 먼저 본다
후보 이름 하나하나에 대해 둘을 부른다.
query_concepts({ filter: '<이름>' })— 비슷한 이름이 이미 있나find_evidence({ title: '<이름>' })— 다른 이름으로 이미 들어와 있나
있으면 새로 만들지 않는다. 둘 중 하나를 한다 —
patch_concept(expected_mtime 함께)로 내용을 채우거나, 관계만 더한다.
- 글에 없는 것은 만들지 않는다
산문은 사람이 대충 쓴다. 「~하면 좋겠다」 · 「~일 수도 있다」 는 아직 사실이 아니라 바람이다. 글이 실제로 주장하는 것만 후보로 올린다. 애매하면 후보에는 올리되 「글의 근거가 약함」이라고 적어서 사람이 판단하게 한다.
- 승인된 것만 쓴다 — 그리고 확인한다
- 파일이면
absorb_document({ filePath, confirm: true }) - 붙여 넣은 글이면
add_concepts→ (전부 성공한 뒤)add_relations - 그다음
validate_vault({})→query_ontology({ operation: 'health' })
이름은 이 볼트가 쓰는 방식대로
title 은 검색이 기준으로 삼는 단 하나의 정본 이름이라 볼트 안에서 언어가
하나로 통일돼야 한다. 섞이면 검색이 갈린다. 다른 언어 이름은 display_ko /
display_en 에 넣는다. 지금 이 볼트가 어느 쪽인지는 list_concepts 로 먼저 본다.
이 스킬이 실패하는 방식
- 글에 없는 개념을 그럴듯하게 지어낸다
- 이미 있는 개념을 이름만 바꿔 또 만든다
confirm: true를 먼저 불러 사람이 보기 전에 써 버린다title언어를 볼트와 다르게 넣어 검색이 갈린다
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.
- 12d ago First seen · 54 lines · 76 tokens per session scan A cd85e2e3b0d3
atlas-absorb is a skill published in the GitHub repository wlsdks/ontology-atlas (104 stars, last pushed today), licensed MIT. It adds 76 tokens to every session and 727 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 2026-08-30.
Other skills, from other repositories
notion-knowledge-management
Creates Notion pages and databases, applies templates for research docs, ADRs, and specs, and manages team knowledge bases. Use when creating Notion pages, structuring databases, documenting decisions, or capturing research findings.
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…
vault
Search, read, write, and manage files in the Kept conversation vault. Use when the user asks about past conversations, wants to save notes, needs to find specific content, or wants to organize their vault.