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 Knuckles-Team/epistemic-graph --skill kg-modality-sparqlgit clone --depth 1 https://github.com/Knuckles-Team/epistemic-graphWrote 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/knuckles-team/epistemic-graph/kg-modality-sparql)<a href="https://agentmods.dev/skills/knuckles-team/epistemic-graph/kg-modality-sparql"><img src="https://agentmods.dev/badge/skills/knuckles-team/epistemic-graph/kg-modality-sparql/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/knuckles-team/epistemic-graph/kg-modality-sparql"><img src="https://agentmods.dev/badge/skills/knuckles-team/epistemic-graph/kg-modality-sparql.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 | $0.00114 | $0.00843 |
| Opus 5.5 | $0.00046 | $0.00337 |
| Sonnet 5.5 | $0.00023 | $0.00169 |
| Haiku 4.5 | $0.00011 | $0.00084 |
Grade A, and why
kg-modality-sparql 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 1mo 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.
curl -s 'http://127.0.0.1:7878/sparql' \ How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kg-modality-sparql — RDF/SPARQL over the engine wire
The engine is a first-class SPARQL 1.1 endpoint (eg-rdf crate). It serves the full query
matrix — SELECT/ASK/CONSTRUCT/DESCRIBE, BGP + property paths, OPTIONAL/UNION/MINUS,
aggregates, sub-SELECT, VALUES, true named graphs (FROM/FROM NAMED/GRAPH ?g), SPARQL
1.1 UPDATE (INSERT/DELETE DATA, DELETE/INSERT WHERE, CREATE/DROP GRAPH), SHACL/ShEx
validation and SERVICE federation. RDF-star and the JSON-LD/TriG/N-Quads/RDF-XML
serialization matrix are supported. See docs/capabilities.md → SPARQL (eg-rdf).
The wire way (epistemic-graph owns it)
The /sparql HTTP listener (feature sparql-http) is opt-in: build with sparql-http
and set EPISTEMIC_GRAPH_SPARQL_ADDR (--sparql-addr, default 127.0.0.1:7878). Any
existing SPARQL client then works unchanged (W3C SPARQL 1.1 Protocol, GET + POST):
# query
curl -s 'http://127.0.0.1:7878/sparql' \
--data-urlencode 'query=SELECT ?s ?p ?o WHERE { ?s ?p ?o } LIMIT 5'
# update
curl -s 'http://127.0.0.1:7878/sparql' \
--data-urlencode 'update=INSERT DATA { <urn:a> <urn:knows> <urn:b> }'
Content negotiation returns SPARQL-results JSON/XML/CSV/TSV (or Turtle/N-Triples for
CONSTRUCT/DESCRIBE). Full recipe + env table: docs/interfaces/connecting.md → SPARQL 1.1.
The MCP way (through graph-os)
load_tools(tools=["engine_rdf"]) # then call engine_rdf with a SPARQL query/update
or the REST twin exposed by graph-os for the RDF modality.
Cross-modal seam
The triplestore is not a silo: RDF triples live in the same store as the SQL nodes
table, vectors, and time-series, so a SPARQL write participates in the engine's unified
cross-modal ACID transaction (graph + RDF + vector + blob in one WriteTransaction), and
OWL reasoning (kg-modality-reasoning) materializes inferences over the same triples.
Related
kg-modality-reasoning— OWL-RL/DL inference + materialization over these triples.kg-modality-sql— the SQL wire onto the same nodes; JOINable across modalities.
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.
- 1mo ago First seen · 61 lines · 114 tokens per session scan A 2ad4e4063fd3
kg-modality-sparql is a skill published in the GitHub repository Knuckles-Team/epistemic-graph (11 stars, last pushed 3d ago), licensed MIT. It adds 114 tokens to every session and 843 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
open-ontologies
AI-native ontology engineering using 110 MCP tools backed by an in-memory Oxigraph triple store. Build, validate, query, and govern RDF/OWL ontologies with a generate-validate-iterate loop. Use when building ontologies, knowledge graphs, RDF data, SPARQL queries, BORO/4D modeling, SHACL validation, clinical…
semantic-web
Design Semantic Web structures, Ontologies, and Meta-knowledge graphs.
mcp-sparql
Exposes SPARQL query capabilities to LLMs via the Model Context Protocol. Supports SELECT, ASK, CONSTRUCT, and DESCRIBE queries against any SPARQL endpoint.
knowledge-graph-sparql
Knowledge graph construction, SPARQL querying, and entity linking for library and research data management using RDF and Wikidata.
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.