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 voro6yov/spec-driven-development --skill query-derivationgit clone --depth 1 https://github.com/voro6yov/spec-driven-developmentWrote 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/voro6yov/spec-driven-development/query-derivation)<a href="https://agentmods.dev/skills/voro6yov/spec-driven-development/query-derivation"><img src="https://agentmods.dev/badge/skills/voro6yov/spec-driven-development/query-derivation/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/voro6yov/spec-driven-development/query-derivation"><img src="https://agentmods.dev/badge/skills/voro6yov/spec-driven-development/query-derivation.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00051 | $0.02001 |
| Opus 5.5 | $0.00020 | $0.00800 |
| Sonnet 5.5 | $0.00010 | $0.00400 |
| Haiku 4.5 | $0.00005 | $0.00200 |
Grade A, and why
query-derivation 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 12d 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Query Part Derivation
Purpose
A domain diagram in this project has a command part (the aggregate root, its
Command<X>Repository, child entities / value objects, domain events, and
<<TypedDict>> data structures) and a query part (the read-side classes).
The query part is almost entirely a mechanical projection of the command part.
This skill is the single source of truth for that projection. It is consulted by:
model-diagrams:derive-query-part— the orchestrator skill that interviews the user and delegates the write.model-diagrams:query-part-deriver— the agent that parses the command part and writes the query classes in place.
Both must derive identical output from identical input; divergence between them is a bug in whichever one drifted from this skill.
Command-part inputs
From the classDiagram block, identify:
<X>— the single<<Aggregate Root>>class. Its private fields (-name) and its computed properties (+status) are the source of the read model.Command<X>Repository— the<<Repository>>whose name starts withCommand. Its lookup methods seed the query repository.- Child classes — every
<<Entity>>/<<Value Object>>reachable from<X>through composition (*--) or aggregation (o--). - Command-side
<<TypedDict>>—*Datatypes and shared types (e.g.Globals,ParsingError). These are reuse candidates (see Type reuse rule).
Domain events, domain services, and Command<X>Repository itself are not
projected — the query part ignores them.
<x> below is the aggregate name in snake_case; <X> is the class name.
Query-part outputs
Emit these six class kinds, in this order, at the tail of the classDiagram
block — after the last command class, before the closing ```.
1. Query<X>Repository <<Repository>>
find_<x>(<x>_id: str) <X>Info | None— always emitted; the projection ofCommand<X>Repository.<x>_of_id.- For each alternate lookup on the command repository — any method returning
the aggregate
<X>that is not<x>_of_id(e.g.template_of_source_id,project_with_details) — afind_<x>_by_<thing>(<same params>) <X>Info | None.<thing>is the distinguishing noun (template_of_source_id→find_template_by_source;project_with_details→find_project_by_details). Whether each alternate lookup is projected is a feedback point (see below). find_<x>s(filtering: <X>Filtering | None, pagination: Pagination | None) <X>ListResult— always emitted.has_*methods,save, anddeleteare never projected.
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.
- 12d ago First seen · 172 lines · 51 tokens per session scan A ce1ebe31245b
query-derivation is a skill published in the GitHub repository voro6yov/spec-driven-development (5 stars, last pushed 13d ago), licensed Apache-2.0. It adds 51 tokens to every session and 2,001 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-04.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…