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 Kromatic-Innovation/athenaeum --skill adapter-authoringgit clone --depth 1 https://github.com/Kromatic-Innovation/athenaeumWrote 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/kromatic-innovation/athenaeum/adapter-authoring)<a href="https://agentmods.dev/skills/kromatic-innovation/athenaeum/adapter-authoring"><img src="https://agentmods.dev/badge/skills/kromatic-innovation/athenaeum/adapter-authoring/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/kromatic-innovation/athenaeum/adapter-authoring"><img src="https://agentmods.dev/badge/skills/kromatic-innovation/athenaeum/adapter-authoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
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 →
- high YARA Match · line 3 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- high Prompt Injection · line 129 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00086 | $0.02095 |
| Opus 5 | $0.00043 | $0.01047 |
| Sonnet 5 | $0.00017 | $0.00419 |
| Haiku 4.5 | $0.00009 | $0.00210 |
Grade A, and why
adapter-authoring 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 5d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
adapter-authoring
Teach the user (or yourself, as an agent) how to build a source adapter for Athenaeum: a script or integration that turns an external source into raw-intake files the librarian compiles into the wiki. This skill is self-contained — it does not depend on any private Kromatic repo or context.
The authoritative contract this skill operationalises is
docs/extending/adapter-contract.md.
The runnable reference is
examples/adapters/minimal_adapter.py.
This skill file ships inside the published athenaeum package (under skills/);
the contract doc and example live in the repository and the source distribution
(links above), so it stays self-contained however it was installed.
Not the same thing as a store adapter. This skill is about a source
adapter — turning external data into raw/ intake files, per
docs/extending/adapter-contract.md above. If instead you are implementing a whole
physical storage backend (e.g. so athenaeum can persist its knowledge
root somewhere other than a local filesystem — an object store, a database),
that is the Store protocol, and it has its own contract and its own
runnable conformance harness:
docs/extending/store-contract.md— the publishedStorecontract (issue athenaeum#983).athenaeum.store_conformance.StoreConformanceTests— subclass it, override itsstorefixture with your ownStoreimplementation, and run pytest; seedocs/extending/store-contract.md's "Running the conformance harness against your own implementation" section for the exact shape, andtests/test_store_conformance_harness.pyin the athenaeum repo for a complete worked example.
The two adapters never collide (same non-overlap docs/extending/storage-adapter-contract.md
draws between the storage-adapter layer and this skill's intake adapters): an
intake adapter turns an external source into raw/ files and stops at
"how data enters the pipeline"; a Store implementation governs how the
already-compiled wiki is physically read and written. If you're feeding a new
external source in, keep reading this skill. If you want athenaeum's
knowledge root to live on a different physical backend, go to
docs/extending/store-contract.md instead.
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.
- 5d ago Changed c813432976e3
- 11d ago First seen · 138 lines · 86 tokens per session scan A 45b0d8687b7d
adapter-authoring is a skill published in the GitHub repository Kromatic-Innovation/athenaeum (12 stars, last pushed today), licensed Apache-2.0. It adds 86 tokens to every session and 2,095 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
pinecone-research
Agent RAG and long-term memory with Pinecone.
browserwing-admin
Manage and operate BrowserWing — an intelligent browser automation platform. Install dependencies, configure LLM, create/manage/execute automation scripts, use AI-driven exploration to generate scripts, browse the script marketplace, and troubleshoot issues.
karpathy-llm-wiki
Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.
local-embedding
Run embedding on-device with ONNX Runtime. Build from source, model selection, offline mode. Use when setting up local embedding without an API key.
dify
Use when building LLM applications with visual workflow — RAG knowledge bases, AI agents, chatbots with drag-and-drop orchestration. Dify: open-source LLM app platform supporting 30+ models (OpenAI, Claude, DeepSeek, Ollama, Qwen, GLM) with Docker deployment.
memory-lancedb
LanceDB-backed vector memory for high-volume embedding and retrieval workloads.