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 spyrae/kronos-agent-os --skill marketplace-comparegit clone --depth 1 https://github.com/spyrae/kronos-agent-osWrote 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/spyrae/kronos-agent-os/marketplace-compare)<a href="https://agentmods.dev/skills/spyrae/kronos-agent-os/marketplace-compare"><img src="https://agentmods.dev/badge/skills/spyrae/kronos-agent-os/marketplace-compare/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/spyrae/kronos-agent-os/marketplace-compare"><img src="https://agentmods.dev/badge/skills/spyrae/kronos-agent-os/marketplace-compare.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 | $0.00025 | $0.00592 |
| Opus 5 | $0.00013 | $0.00296 |
| Sonnet 5 | $0.00005 | $0.00118 |
| Haiku 4.5 | $0.00003 | $0.00059 |
Grade A, and why
marketplace-compare 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Marketplace Compare
The number that matters
Not the price. The landed cost: price plus shipping plus insurance plus any import duty and payment fee — what leaves the owner's account for the thing to arrive at their door.
Feed it to compare_offers with price as recurring (one period) and shipping,
duty and fees as one-off. It will refuse to rank a listing whose shipping nobody
stated, and that refusal is the point: a missing figure is not a zero one, and a
listing that does not state its shipping is not the cheapest one.
Different currencies do not add up. Convert first, say what rate you used, or compare within one currency and say so.
Reading a seller
A rating without a volume means nothing. 4.9 across 3,000 sales beats 5.0 across 12, and the second looks better in every table that sorts on rating alone. Collect together, and hand them to the owner rather than scoring them:
- rating and number of ratings
- how long the store has existed
- how fast it responds
- whether the photographs are the seller's own or the manufacturer's
Do not rank on any of this. The trade between "cheapest" and "a shop that has been there four years" is the owner's to make, and a weight invented in code makes it silently.
Signs of a grey unit
For electronics especially, worth naming:
- priced well below the cluster with nothing explaining it
- warranty from the shop rather than the manufacturer
- "ready stock" on a listing created days ago
- stock photographs only, no photo of the actual box
- a region or model variant that differs from what the local distributor sells — the practical cost is that nobody local will service it
None of these means "do not buy". They mean "the owner should know before buying".
Method
- Fetch each product page directly (
fetch_page). Search pages reorder and go stale; a product page is the claim. - Extract into one shape (
extract_structured) — seestructured-extraction. - Total with
compare_offers. - Report the ranking, the sellers, and anything odd.
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 · 70 lines · 25 tokens per session scan A 29092a894aa1
marketplace-compare is a skill published in the GitHub repository spyrae/kronos-agent-os (49 stars, last pushed 2d ago), licensed MIT. It adds 25 tokens to every session and 592 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 2026-08-30.
Other skills, from other repositories
python-lib-analyzer
Analyze any Python library structure, explore modules, classes, and functions with signatures and documentation.
data-visualization
Use for creating publication-quality charts and multi-panel analysis summaries. Triggers when tasks involve visualizing data, plotting results, creating charts, or producing visual reports from analysis output.
cuml-machine-learning
Use for GPU-accelerated machine learning on tabular data using NVIDIA cuML. Triggers when tasks involve classification, regression, clustering, dimensionality reduction, or model training on datasets.
remember
Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback — into persistent memory (AGENTS.md) or reusable skills. Use when the user says: (1) remember this, (2) save what we learned, (3) update memory, (4) capture…
schema-exploration
Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.
deepagents-thread-inspector
Inspect and explain conversations in the local Deep Agents Code SQLite session store. Use as a fallback when LangSmith trace tooling is unavailable, for offline or untraced sessions, or when asked to identify or summarize a local dcode thread, inspect checkpoint metadata, list recent local threads, or parse…