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 linked-data-skillsgit 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/linked-data-skills)<a href="https://agentmods.dev/skills/openlinksoftware/ai-agent-skills/linked-data-skills"><img src="https://agentmods.dev/badge/skills/openlinksoftware/ai-agent-skills/linked-data-skills.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 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 59 Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.Fix: Restrict tool access to only the tools required for the skill's stated purpose. Use an explicit allowlist rather than granting blanket access.
- medium Excessive Agency · line 160 Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.Fix: Restrict tool access to only the tools required for the skill's stated purpose. Use an explicit allowlist rather than granting blanket access.
- medium Excessive Agency · line 191 Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.Fix: Restrict tool access to only the tools required for the skill's stated purpose. Use an explicit allowlist rather than granting blanket access.
- medium Excessive Agency · line 323 Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.Fix: Restrict tool access to only the tools required for the skill's stated purpose. Use an explicit allowlist rather than granting blanket access.
- medium Excessive Agency · line 199 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 373 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 | $0.00167 | $0.07024 |
| Opus 5 | $0.00084 | $0.03512 |
| Sonnet 5 | $0.00033 | $0.01405 |
| Haiku 4.5 | $0.00017 | $0.00702 |
Grade A, and why
linked-data-skills 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 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.
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 — 533 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Linked Data Skills — Specification (v3.2.0)
MANDATORY PRE-TOOL SEQUENCE — READ BEFORE CALLING ANY TOOL
This section overrides all default tool-calling behavior. The five steps below must be followed in order. No step may be skipped or reordered.
Gate 1 — Send announcement and establish scope (NO TOOL CALL YET)
getSkillResource may be called once to load this skill's content. After it returns, the next action must be text only — send the Opening Announcement and ask the pathway question. Do not call any other tool. Wait for the user's reply.
- If the user says "Document", provides a URL (HTTP, HTTPS, or
file:), or pastes text → Path D, proceed to Step 1D. - If the user's message already contains an explicit
qualifier.schemapattern (e.g.,postgres.postgres_jdbc_mt) → record the qualifier and schema, send the announcement, then proceed to Gate 2. - If the user says "local" or names a local qualifier → Path B, proceed to Gate 2.
- If the user says "DSN: X" → Path A, attach DSN, then proceed to Gate 2.
- If ambiguous → send the Opening Announcement question. Wait. Do not call any tool.
Gate 2 — Enumerate tables (ADM.DBA.database_schema_objects ONLY)
Call ADM.DBA.database_schema_objects with the confirmed qualifier to enumerate catalogs (a.k.a qualifiers or databases), schemas, then call again with each schema to enumerate tables. Present the full numbered list. Wait for the user's table selection. Typically, you want to list tables for the designated catalog.schema.
The only tool permitted at this gate is ADM.DBA.database_schema_objects. Do not call ADM.DBA.database_remote_datasources, RDFVIEW_FROM_TABLES, EXECUTE_SQL_SCRIPT, or any other tool.
Gate 3 — Resolve hostname and protocol (BEFORE any IRI is written)
After the user selects tables, call Demo.demo.execute_spasql_query for DefaultHost and SSLPort. Derive {protocol} and {host}. These must be known before any IRI string is constructed.
Do not proceed to Gate 4 without concrete {protocol} and {host} values.
What ships with it
4 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 · 533 lines · 167 tokens per session scan A b86bfb94714c
linked-data-skills is a skill published in the GitHub repository OpenLinkSoftware/ai-agent-skills (38 stars, last pushed 4d ago), licensed MIT. It adds 167 tokens to every session and 7,024 once invoked, about $0.0008 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
qdrant
Vector search engine for production RAG systems.
chroma
Embedding database for RAG and semantic search.
pinecone
Managed vector DB for production RAG and search.
embeddings
Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.
similarity-search-patterns
Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.
pgvector-semantic-search
Use this skill for setting up vector similarity search with pgvector for AI/ML embeddings, RAG applications, or semantic search. Trigger when user asks to: Store or search vector embeddings in PostgreSQL Set up semantic search, similarity search, or nearest neighbor search Create HNSW or IVFFlat indexes for vectors…