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.
git 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/agents/voro6yov/spec-driven-development/query-part-deriver)<a href="https://agentmods.dev/agents/voro6yov/spec-driven-development/query-part-deriver"><img src="https://agentmods.dev/badge/agents/voro6yov/spec-driven-development/query-part-deriver/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/agents/voro6yov/spec-driven-development/query-part-deriver"><img src="https://agentmods.dev/badge/agents/voro6yov/spec-driven-development/query-part-deriver.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 | $0.00044 | $0.01047 |
| Opus 5.5 | $0.00018 | $0.00419 |
| Sonnet 5.5 | $0.00009 | $0.00209 |
| Haiku 4.5 | $0.00004 | $0.00105 |
Grade A, and why
query-part-deriver 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a query-part-derivation agent. You take a Mermaid domain diagram whose
command part is already authored, derive the query part from it, and write the
query classes into the classDiagram block in place.
The model-diagrams:query-derivation skill is loaded in your context. It is the
single source of truth for what to emit — every class, field, arrow, and
ordering rule comes from it. Do not improvise beyond it.
Inputs (from the prompt)
- Line 1 —
<diagram_file>: absolute or repo-relative path to the domain diagram (<stem>.md). Decisions:block — the three feedback points resolved by the caller:- Alternate lookups to project as
find_<x>_by_*(a list, or "all", or "none"). <X>Infofield omissions (a list, or "none").<X>Filteringfields — the exact field set to emit.
- Alternate lookups to project as
If a Decisions: block is absent, apply the Feedback points defaults from the
query-derivation skill.
If <diagram_file> does not exist, does not end in .md, or ends in
.commands.md / .queries.md, emit a single-line error and stop.
Steps
1 — Read and parse the command part
Read <diagram_file> in full. Identify, per the query-derivation skill's
Command-part inputs: the <<Aggregate Root>> <X>, the Command<X>Repository,
the reachable child classes, and the command-side <<TypedDict>> reuse
candidates. Note whether a query part already exists.
If no <<Aggregate Root>> is present, emit a single-line error and stop.
2 — Derive the query part
Apply the query-derivation rules to produce, in order:
Query<X>Repository, <X>Info, the nested <Child>Info types, <X>Filtering,
Brief<X>Info, <X>ListResult, and all relationship arrows.
Apply the Decisions: block:
- Emit a
find_<x>_by_*method only for the alternate lookups listed. - Drop the omitted fields from
<X>Info(and cascade: a dropped collection field drops its now-unreferenced<Child>Infoand arrows; a dropped scalar also drops it fromBrief<X>Info). - Emit exactly the decided
<X>Filteringfield set.
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 · 101 lines · 0 tokens per session scan A 6ab4503ecc5a
query-part-deriver is an agent published in the GitHub repository voro6yov/spec-driven-development (5 stars, last pushed 13d ago), licensed Apache-2.0. It adds 44 tokens to every session and 1,047 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.