query-pkg SKILL.md skillA
query-pkg from sparq-org/sparq is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add sparq-org/sparq/query-pkg@git:20261005.afb6badPins git:20261005.afb6bad in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- sparq-org/sparq
- Path
.claude/skills/query-pkg/SKILL.md- Versions recorded
- 6
- Latest version
- git:20261005.afb6bad, committed Oct 5, 2026
- First version recorded
- Jun 22, 2026
- Size
- 22,400 bytes
- Repository stars
- 13
- License
- MIT
Answer a "what does the repo say about X, where was Y decided, what is the status or provenance of Z, which sources are still unexplored, what depends on bead W" question by running a SPARQL query over the ingested Project-Knowledge-Graph (PKG) instead of reading whole documents. Use when an agent working on sparq needs a sourced, answer-sized fact from AGENTS.md, the skills, or the bd backlog and would otherwise Read or Grep a large doc. The mechanism is introspect then ground then ask via…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Query the PKG — introspect → ground → ask Bead **sq-2m6zm.3** (epic sq-2m6zm). Design record: `research/dogfooding-sparq-knowledge-graph.md` (§4.1 frontier queries, §6 worked questions). 🤖 SPARQ agent — dogfooding sparq as a project knowledge graph. The PKG is sparq's own knowledge stored as RDF triples: `pkg:Finding`s (sourced, confidence-tagged discoveries from AGENTS.md), `pkg:Source`s (skills / docs with an explored-status), `pkg:Technique`s (the surfaces), and `pkg:Task`s (the bd backlog projected to RDF with `pkg:dependsOn` edges). Instead of `Read`-ing a whole document to find one fact, run a SPARQL query and read the **answer-sized** result. The answer is computed by sparq's own engine over the ingested graph — within the store the agent cannot fabricate a fact the data does not contain (the engine bounds the result set), and an empty result is the honest "I don't know / none outstanding" answer. > **Honesty.** This skill is the *mechanism*. The cost saving versus reading the source > document is now **MEASURED** (bead **sq-zbyo7**, the agent-flavour cheap-model NL-tool: > ≈ 30× cheaper in $ than read-docs at equal quality on PKG-answerable tasks); the full …
Read the whole file at its exact version.
How to install
mdr add sparq-org/sparq/query-pkg@sha256:7ea495a8fc133afbThe line at the top of this page pins the label git:20261005.afb6bad, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_522p4jz7qjbfrizd)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 6 versions of this file, between Jun 22, 2026 and Oct 5, 2026, about one every 21 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261005.afb6bad latest | 2026-10-05 | afb6bad | 22,400 B | A | view · diff |
| git:20260712.dd54cfa | 2026-07-12 | dd54cfa | 22,526 B | A | view · diff |
| git:20260710.9984288 | 2026-07-10 | 9984288 | 22,239 B | A | view · diff |
| git:20260705.582a3ce | 2026-07-05 | 582a3ce | 21,863 B | A | view · diff |
| git:20260623.f3b979c | 2026-06-23 | f3b979c | 20,544 B | A | view · diff |
| git:20260622.28e95d0 | 2026-06-22 | 28e95d0 | 18,414 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (22400 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
sparq-org/sparq · 13 stars · license MIT · pushed 2026-10-29 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_522p4jz7qjbfrizd GET https://markdownregistry.com/api/v1/resolve?ref=sparq-org/sparq/query-pkg GET https://markdownregistry.com/api/v1/blob/7ea495a8fc133afbd4373244a559e5722a253b2315def31e6bc7b2ac0d212e92
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.