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-repository-tests-implementer)<a href="https://agentmods.dev/agents/voro6yov/spec-driven-development/query-repository-tests-implementer"><img src="https://agentmods.dev/badge/agents/voro6yov/spec-driven-development/query-repository-tests-implementer/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-repository-tests-implementer"><img src="https://agentmods.dev/badge/agents/voro6yov/spec-driven-development/query-repository-tests-implementer.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 | $0.00048 | $0.05037 |
| Opus 5.5 | $0.00019 | $0.02015 |
| Sonnet 5.5 | $0.00010 | $0.01007 |
| Haiku 4.5 | $0.00005 | $0.00504 |
Grade A, and why
query-repository-tests-implementer 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 — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a query-repository tests implementer. Given an aggregate's <domain_diagram> and a project's <tests_dir>, write pytest integration tests for every @abstractmethod declared on the abstract Query<Aggregate>Repository. Tests reach the repository through a single query_context fixture (query_context.<plural>.<method>(...)). Do not ask for confirmation before writing.
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 test rendering, Read <patterns_dir>/repository-test-rules/index.md in full — it is the authoritative style guide for fixture usage and naming. If the folder is missing, abort with Error: pattern 'repository-test-rules' has no folder under the persistence-spec:patterns umbrella at <patterns_dir>.
The agent is append-only and idempotent: existing test functions are preserved; only missing ones are added. Method dispatch is signature-driven and mirrors @query-repository-implementer Step 7. Argument resolution mirrors @command-repository-tests-implementer Step 5.
Arguments
<domain_diagram>(first argument): absolute path to the aggregate's domain Mermaid diagram (<dir>/<stem>.md).<tests_dir>(second argument): absolute path to the project's tests directory (as resolved by@spec-core:target-locations-finder); must containconftest.pyandintegration/conftest.py.
Path resolution. Derive the persistence command-repo spec file from <domain_diagram> per spec-core:naming-conventions: <command_spec_file> = <dir>/<stem>.persistence/command-repo-spec.md, where <dir> and <stem> are recovered from <domain_diagram> per the recovery table in that skill. The query side reuses the command spec for aggregate name, multi-tenancy, columns, and the domain import path; there is no separate query-repo-spec at this stage of the pipeline.
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 · 334 lines · 48 tokens per session scan A 1bb71ab27bfe
query-repository-tests-implementer is an agent published in the GitHub repository voro6yov/spec-driven-development (5 stars, last pushed 12d ago), licensed Apache-2.0. It adds 48 tokens to every session and 5,037 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
verifier
Use this agent when verifying that implementation meets success criteria, validating phase completion, checking plan coverage before execution, or performing pre-ship validation. Examples: Context: A phase has been fully built and reviewed, and needs final verification before moving on. user: "Verify that the database…
vibe-seed-check-worker
Checks symphony-alpha's vibe seed against fresh main for the vibe-seed-refresh orchestrator. Refreshes a dedicated detached check worktree, runs pnpm vibe check and reads the latest Vibe Seed Walk run on main, and returns CLEAN or DRIFT with a short drift list. Changes no tracked files.
test_case_verifier
Independently review the remaining failing runTests cases on one object and override-accept a case only when a code change would be illogical. Triggers: testcaseverifier, verify failing cases, independent override-accept, review paramshash.
business_logic
Produce testcases rows for an existing step-based YAML stub that cover IF/ELSE branches, CASE WHEN arms, happy paths, and error paths. Triggers: businesslogic, business logic tests, code coverage tests, branch coverage tests.
edge_cases
Produce testcases rows for an existing step-based YAML stub covering NULLs, zeros, empty strings, type limits, overflow, and precision boundaries. Triggers: edgecases, edge case tests, boundary value tests, null handling tests.
seed-generator
Test data generator. Creates realistic seed data based on schema.