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 OpenLinkSoftware/ai-agent-skills --skill kg-generatorgit clone --depth 1 https://github.com/OpenLinkSoftware/ai-agent-skillsWrote 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/openlinksoftware/ai-agent-skills/kg-generator)<a href="https://agentmods.dev/skills/openlinksoftware/ai-agent-skills/kg-generator"><img src="https://agentmods.dev/badge/skills/openlinksoftware/ai-agent-skills/kg-generator/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/openlinksoftware/ai-agent-skills/kg-generator"><img src="https://agentmods.dev/badge/skills/openlinksoftware/ai-agent-skills/kg-generator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 8 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 Data Exfiltration · line 137 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Excessive Agency · line 266 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 435 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 613 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 738 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 850 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 960 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 1136 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 | $0.00089 | $0.34330 |
| Opus 5 | $0.00044 | $0.17165 |
| Sonnet 5 | $0.00018 | $0.06866 |
| Haiku 4.5 | $0.00009 | $0.03433 |
Grade B, and why
kg-generator scanned grade B with 2 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 8d 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
- Navigate: `curl -X POST http://localhost:9867/navigate -d '{"url":"..."}'` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
1. Direct native access (file read, WebFetch, or `curl`) to the source URL How it starts
The opening of the file, as written. The whole thing — 1,300 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Graph Generator Skill
Generate comprehensive, standards-compliant Knowledge Graphs from any file: or http[s]: URL. Produces RDF-Turtle by default; JSON-LD and other serializations available on request.
When to Use This Skill
- "Generate a knowledge graph from [URL]"
- "Generate RDF / RDF-Turtle from [URL]"
- "Generate JSON-LD from [URL]"
- "Convert this page to structured semantic data"
- "Extract schema.org data from [URL]"
- "Create an RDF rendition of this post/article/report"
Harness Alignment
This skill is a Knowledge Graph generation entry point. For document/source-to-RDF requests, interpret the request through the document-to-kg-skill Document-to-KG Harness Mode contract when that skill is available. For requests that also ask for HTML, Markdown, an infographic, or a KG Explorer, hand off to the rdf-infographic-skill RDF Infographic Harness Mode after RDF generation.
Do not let this skill drift into standalone HTML generation, source summarization, or manually invented graph visualization. RDF remains the source of truth, and companion HTML/Markdown artifacts must satisfy the RDF/HTML/MD pairing contract in rdf-infographic-skill.
Narrative and Visual-Communication Contract
When the RDF will drive a reader-facing document, model a coherent evidence-backed narrative spine rather than an undifferentiated fact inventory. Preserve the source's thesis, contrasts, causal chain, quantitative evidence, limitations, and conclusion as ordered, queryable entities and relationships. Model comparison dimensions, metric observations, claims, provenance, and SPARQL recipes explicitly so the companion document can communicate them through the most appropriate visual form.
For any visual or interactive companion, operate as a UI/UX expert, visual-communications designer, and storyteller, and inherit the full rdf-infographic-skill operating modality. The reader journey must determine hierarchy and pacing; tables serve exact comparisons, flows serve sequence or causality, diagrams serve architecture, charts serve quantitative patterns, and prose serves interpretation. Live SPARQL interaction is part of the story surface when it lets readers test or extend the document's claims; it must not be relegated to decorative or disconnected query text.
What ships with it
6 files 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.
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.
- 8d ago First seen · 1,300 lines · 89 tokens per session scan B dd257bcfe996
kg-generator is a skill published in the GitHub repository OpenLinkSoftware/ai-agent-skills (38 stars, last pushed 5d ago), licensed MIT. It adds 89 tokens to every session and 34,330 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.