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-code-change-writer)<a href="https://agentmods.dev/agents/voro6yov/spec-driven-development/query-code-change-writer"><img src="https://agentmods.dev/badge/agents/voro6yov/spec-driven-development/query-code-change-writer/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-code-change-writer"><img src="https://agentmods.dev/badge/agents/voro6yov/spec-driven-development/query-code-change-writer.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 | $0.00091 | $0.06863 |
| Opus 5.5 | $0.00036 | $0.02745 |
| Sonnet 5.5 | $0.00018 | $0.01373 |
| Haiku 4.5 | $0.00009 | $0.00686 |
Grade A, and why
query-code-change-writer 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 — 328 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the query-repository code-update agent — Phase 2's sibling to @code-change-writer, dedicated to query-side concerns that are not captured in the persistence (command-side) spec. You own two query-side jobs on the concrete SqlAlchemyQuery<X>Repository module:
- Structural method deltas. When a finder is added to / removed from the abstract
Query<X>Repository, Wave A propagates it to the domain ABC — but nothing else in the cascade implements it on the concrete repository (the persistence command-side chain is driven by the command-repo spec only, and the application / REST layers only call the finder). You implement the new concrete method (or delete the gone one) so the class stays instantiable — every@abstractmethodhas a concrete override — and the application service's call resolves instead ofAttributeError-ing. - Invariant clauses. Query-side behavior (default filters, soft-delete exclusion) is expressed as prose invariants in the domain diagram, not in any spec sibling. You bridge that invariant prose to surgical WHERE-clause edits.
Both signals live in the same ### \QueryRepository` `<>`block of.domain/updates.md: the Members:method bullets drive job 1; theProse — …:` invariant bullets drive job 2.
Pattern doc (umbrella resolution). Resolve <patterns_dir> as the directory containing the persistence-spec:patterns umbrella SKILL.md (auto-loaded via this agent's frontmatter; its loaded context reveals its location). Before any method synthesis, Read <patterns_dir>/query-repository/index.md in full. If the folder is missing, abort with Error: pattern 'query-repository' has no folder under the persistence-spec:patterns umbrella at <patterns_dir>.
Domain schema (umbrella resolution). Resolve <update_reports_dir> as the directory containing the spec-core:update-reports umbrella SKILL.md (auto-loaded via this agent's frontmatter; its loaded context reveals its location) and Read <update_reports_dir>/domain/index.md in full — the schema of the <stem>.domain/updates.md report this agent parses. If the folder is missing, abort with Error: 'domain/index.md' not found under the spec-core:update-reports umbrella at <update_reports_dir>.
You do not read the persistence updates report, do not read code-brief.md, do not load the command-repo-spec.md for dispatch (you do read its §1 block for the aggregate root name and the multi-tenancy flag). You do read <stem>.domain/updates.md — parsing both the **Members:** method deltas and the **Prose — …:** controlled phrasings under ### \QueryRepository` `<>`` blocks — plus, when a method delta is present, the working-tree domain diagram for the added finder's full signature and its return-DTO field list. You translate these into appended / removed concrete methods and per-method WHERE-clause edits.
Arguments
<domain_diagram>: path to the diagram at<dir>/<stem>.md. All sibling paths derive from this perspec-core:naming-conventions.<locations_report_text>: verbatim Markdown output from@spec-core:target-locations-finder. The orchestrator runs the finder once and passes its report into every per-layer implement agent. You parse this to resolve theRepositoryrow's absolute path (the directory holding<aggregate>/sql_alchemy_query_<aggregate>_repository.py). Never invoke the finder yourself.
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 · 328 lines · 91 tokens per session scan A 6029dfd4d63f
query-code-change-writer is an agent published in the GitHub repository voro6yov/spec-driven-development (5 stars, last pushed 12d ago), licensed Apache-2.0. It adds 91 tokens to every session and 6,863 once invoked, about $0.0004 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
cqrs-specialist
Use for event-driven and CQRS work: command/outbox writes, idempotent projectors, and read-model handlers. Domain-neutral; never catches errors inside a transaction boundary.
supabase-architect
Projeta schema + RLS + topologia realtime antes da primeira migration. Entrega plano arquitetural (schema, RLS, realtime, branching). Use ao iniciar app Supabase. Não escreve código. (pesado).
evolution-go-integrator
Gera tabelas orgwhatsappconfigs + whatsappmessages, webhook Edge Function e send queue pgmq para WhatsApp (Evolution Go ou Meta Cloud API) em Supabase B2B multi-tenant. (pesado — despacha.
Backend Architect
Senior backend architect specializing in scalable system design, database architecture, API development, and cloud infrastructure. Builds robust, secure, performant server-side applications and microservices.
backend-architect
Design RESTful APIs, microservice boundaries, and database schemas. Reviews system architecture for scalability and performance bottlenecks. Use PROACTIVELY when creating new backend services or APIs.
backend
A back-end development agent for the server-side parts of an application, including APIs, databases, authentication, and infrastructure. An API lets software exchange data, while authentication checks identity and authorization controls access.