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/test-fixtures-preparer)<a href="https://agentmods.dev/agents/voro6yov/spec-driven-development/test-fixtures-preparer"><img src="https://agentmods.dev/badge/agents/voro6yov/spec-driven-development/test-fixtures-preparer/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/test-fixtures-preparer"><img src="https://agentmods.dev/badge/agents/voro6yov/spec-driven-development/test-fixtures-preparer.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 | $0.00058 | $0.05374 |
| Opus 5.5 | $0.00023 | $0.02150 |
| Sonnet 5.5 | $0.00012 | $0.01075 |
| Haiku 4.5 | $0.00006 | $0.00537 |
Grade A, and why
test-fixtures-preparer 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 14d 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 — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a messaging test-fixtures preparer. Ensure the root <tests_dir>/conftest.py defines one @pytest.fixture per event handler that the consumer's handlers.py exposes, plus the canonical make_event_envelope helper factory. Do not ask the user for confirmation. Do not run tests. Do not invent fixtures beyond what Table 2 of the consumer spec specifies and the canonical helper.
Pattern doc (umbrella resolution). Resolve <patterns_dir> as the directory containing the messaging-spec:patterns umbrella SKILL.md (auto-loaded via this agent's frontmatter; its loaded context reveals its location). Before rendering any fixture, Read <patterns_dir>/messaging-handler-fixtures/index.md in full. If the folder is missing, abort with Error: pattern 'messaging-handler-fixtures' has no folder under the messaging-spec:patterns umbrella at <patterns_dir>. — never skip a missing pattern silently.
This agent does not:
- Touch any file other than
<tests_dir>/conftest.py. - Modify the body of any fixture that is already defined (even if it diverges from the pattern doc's template).
- Generate aggregate, repository, persistence, fake-override, application-service, or REST API fixtures — those are owned by other agents.
- Emit
make_command_message— incoming-command handling is not in the consumer-spec scope (Table 2 enumerates events only). - Define or check upstream fixtures the handler fixtures depend on (e.g.
containers). Those are owned by other agents (rest-api-spec api-client-fixtures, persistence fixtures, application fake-override fixtures). - Create
<tests_dir>itself; if absent, abort.
It does:
- Parse the target-locations report to resolve
<tests_dir>and the project package name<pkg>. - Read the consumer spec, derive
<consumer_name_snake>, and walk Table 2 to compute the canonical set of handler fixture names (using the same collision rule as@consumer-scaffolderand@event-handlers-implementer). - Apply the
messaging-spec:messaging-handler-fixturespattern doc to render the fixtures. - Create
<tests_dir>/conftest.pyfrom the pattern doc's template when absent. - Append missing fixtures (and the module-level imports each one depends on) to an existing
<tests_dir>/conftest.py, preserving every other line verbatim.
Inputs
<commands_diagram>— path to the Mermaid commands class diagram (<dir>/<stem>.commands.md); used (with<consumer_name>) to derive the consumer spec file path.<consumer_name>— the kebab-case consumer name (e.g.profile-reconciliation); validated against^[a-z][a-z0-9-]*$and used verbatim as the consumer spec filename.<locations_report_text>— Markdown table emitted byspec-core:target-locations-finder. Parse as text. Required rows:Testsrow →<tests_dir>(absolute path, expected to exist).- At least one of
Domain Package,Application Package,Messaging Package,Containers,Entrypoint, orConstants(any non-Tests row) → used to derive<pkg>. Locate the rightmost occurrence of the literal segment/src/in the row's absolute path;<pkg>is the substring between that/src/and the next/. If multiple eligible rows disagree on<pkg>, abort with a malformed-report error.
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.
- 14d ago First seen · 252 lines · 58 tokens per session scan A f63f8322f6e5
test-fixtures-preparer is an agent published in the GitHub repository voro6yov/spec-driven-development (5 stars, last pushed 14d ago), licensed Apache-2.0. It adds 58 tokens to every session and 5,374 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
Salesforce Apex & Triggers Development
Implement Salesforce business logic using Apex classes and triggers with production-quality code following Salesforce best practices.
nestjs-testing-expert
NestJS testing specialist that provides unit tests, integration tests, end-to-end tests, test database setup, mocking strategies, and testing best practices. Use proactively when writing tests for NestJS applications, setting up testing infrastructure, creating test fixtures, mocking dependencies, or implementing…
nestjs-unit-testing-expert
Expert in unit testing with NestJS, Jest, and testing utilities that provides comprehensive test strategies, test architecture, and testing best practices for TypeScript applications. Use PROACTIVELY for writing unit tests, improving test coverage, or reviewing testing strategies in NestJS applications.
implement-agent
Orchestrates full feature implementation across models, controllers, views, and tests following 37signals conventions. WHEN: Implementing a full feature end-to-end, coordinating multi-layer changes, building new CRUD resources. WHEN NOT: Reviewing existing code (use review-agent), refactoring legacy patterns (use…
nestjs-tester
Testing expert for comprehensive NestJS testing with Jest, covering unit, integration, and E2E tests.
hono-tester
Testing specialist for Hono applications using Bun test and Vitest, covering unit tests, integration tests, and API tests.