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/sparq-org/sparq/query-pkgnpx skills add sparq-org/sparq --skill query-pkggit clone --depth 1 https://github.com/sparq-org/sparqWrote 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/sparq-org/sparq/query-pkg)<a href="https://agentmods.dev/skills/sparq-org/sparq/query-pkg"><img src="https://agentmods.dev/badge/skills/sparq-org/sparq/query-pkg.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 | $0.00188 | $0.06229 |
| Opus 5 | $0.00094 | $0.03114 |
| Sonnet 5 | $0.00038 | $0.01246 |
| Haiku 4.5 | $0.00019 | $0.00623 |
Grade A, and why
query-pkg 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 5d 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 — 397 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Query the PKG — introspect → ground → ask
[OPUS-4.8] 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:Findings (sourced,
confidence-tagged discoveries from AGENTS.md), pkg:Sources (skills / docs with an
explored-status), pkg:Techniques (the surfaces), and pkg:Tasks (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 table, method, and honest caveats live in
bench/pkg-dogfood/RESULTS.md(the sanctioned measurement record) — this file only points at the headline. The win is scoped to PKG-answerable questions by construction. The PKG is a Phase-1 head slice (the AGENTS.md finding set + a mechanical bd→Task projection + the heaviest skills' front-matter + the trust-graph admission-program provenance tier ofsq-7utko— sourced, caveat-carrying findings fromresearch/trust-graph-authorisation-2026-07.md, e.g. "unlinkability is NOT a v1 guarantee, gated onsq-qhy4"), not the whole corpus — a miss means "not in the head slice yet", so fall back to Read/Grep.
The helper
One command, in crates/sparq-kb, behind the default-OFF query feature (keeps the lean
default build a pure data crate):
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.
- 5d ago First seen · 397 lines · 188 tokens per session scan A b7a661cac57f
query-pkg is a skill published in the GitHub repository sparq-org/sparq (10 stars, last pushed today), licensed MIT. It adds 188 tokens to every session and 6,229 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…