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 agentmods add skills/openlinksoftware/ai-agent-skills/data-twinglernpx skills add OpenLinkSoftware/ai-agent-skills --skill data-twinglergit 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/data-twingler)<a href="https://agentmods.dev/skills/openlinksoftware/ai-agent-skills/data-twingler"><img src="https://agentmods.dev/badge/skills/openlinksoftware/ai-agent-skills/data-twingler.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00139 | $0.07675 |
| Opus 5 | $0.00069 | $0.03837 |
| Sonnet 5 | $0.00028 | $0.01535 |
| Haiku 4.5 | $0.00014 | $0.00768 |
Grade A, and why
data-twingler scanned grade A with 1 finding 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
1. Direct native endpoint calls with `curl` or the query protocol's simplest direct mechanism How it starts
The opening of the file, as written. The whole thing — 632 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenLink Data Twingler (v2.0.86)
Enhances LLM responses with RAG by routing user intent to the right query language and live endpoint. Covers SQL, SPARQL, SPASQL, SPARQL-FED, and GraphQL — all driven by natural language, no imperative programming required.
Defaults & Settings
| Parameter | Value |
|---|---|
| SPARQL Default Endpoint | https://linkeddata.uriburner.com/sparql |
| SPARQL Result Format | text/x-html+tr |
| SPARQL / SQL Timeout | 30 seconds |
| SPARQL Max Results | 20 (unless overridden) |
| Graph IRI Discovery LIMIT | 50 |
| GraphQL Default Endpoint | https://linkeddata.uriburner.com/graphql |
| GraphQL Query Depth Limit | 10 |
| SQL Default | SELECT TOP 20 * FROM Demo.Demo.Customers |
| Cache TTL | 3600 seconds |
| Parallel Execution | Enabled |
| Tabulate All Results | Yes (all query types) |
| Semantic Variant Retries | 3 |
| Fallback Endpoints | https://kingsley.idehen.net/sparql, https://demo.openlinksw.com/sparql |
| Local RDF Directories | Fallback only: ~/Documents/LLMs/*/rdf/, ~/Documents/LLMs/GPT5-Chat-Generated/rdf/, ./rdf/ |
| Auto-Discover Local RDF | Enabled for fallback only — scans model-root RDF directories and ./rdf/ after endpoint exhaustion |
| Vector Similarity Threshold (Local) | 0.75 |
| Vector Candidate Types | schema:Question, schema:DefinedTerm, schema:HowTo, schema:HowToStep, skos:Concept |
| Server-Side Vector Similarity Threshold | 0.5 |
Query Language Routing
Execution Routing
Default execution order for query execution:
- Direct native endpoint calls with
curlor the query protocol's simplest direct mechanism - URIBurner REST functions such as
sparqlRemoteQuery,sparqlQuery,graphqlEndpointQuery,graphqlQuery,execute_spasql_query, andexecute_sql_query - Terminal-owned OAuth flow — when the endpoint requires OAuth 2.0 authentication, execute the OAuth 2.0 flow from the terminal (authorization code, client credentials, or device flow), capture the Bearer token, and inject it into subsequent REST/OpenAPI calls via
Authorization: Bearer {token}headers - MCP via
https://linkeddata.uriburner.com/chat/mcp/messagesorhttps://linkeddata.uriburner.com/chat/mcp/sse - Authenticated LLM-mediated execution via
https://linkeddata.uriburner.com/chat/functions/chatPromptComplete - OPAL Agent routing using recognizable OPAL function names
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.
- 6d ago First seen · 632 lines · 139 tokens per session scan A 0173f3b8e891
data-twingler is a skill published in the GitHub repository OpenLinkSoftware/ai-agent-skills (38 stars, last pushed 2d ago), licensed MIT. It adds 139 tokens to every session and 7,675 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (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
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.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
supabase
Supabase / PostgREST Row-Level-Security playbook — pull the anon (or leaked servicerole) key out of the frontend JS, map tables from the auto-generated OpenAPI spec, test anonymous RLS READ disclosures (PII/secret leaks), and anonymous RLS WRITE abuse (insert/update/delete — e.g. forging…
nornicdb-cypher-queries
Pick fast, predictable Cypher query shapes in NornicDB — point lookups, batch retrieval, pagination, search, traversal, batched UNWIND/MERGE writes, cleanup, multi-tenant isolation. Use when writing or reviewing Cypher whose latency or throughput matters; maps user intent to the executor's hot-path query templates.
dsql
Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, diagnose cluster performance, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, foreign key…
volcengine-rds-postgresql
使用火山引擎 RDS PostgreSQL，帮助用户完成 RDS PostgreSQL 相关的实例管理、数据库操作、账号管理和运维任务，可直接调用 uv run ./scripts/callrdspostgresql.py 脚本获取实时结果。.