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/Enovatr-Labs/SpecRouteWrote 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/enovatr-labs/specroute/unit-test-writer)<a href="https://agentmods.dev/agents/enovatr-labs/specroute/unit-test-writer"><img src="https://agentmods.dev/badge/agents/enovatr-labs/specroute/unit-test-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/enovatr-labs/specroute/unit-test-writer"><img src="https://agentmods.dev/badge/agents/enovatr-labs/specroute/unit-test-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 | $0.00065 | $0.00583 |
| Opus 5.5 | $0.00026 | $0.00233 |
| Sonnet 5.5 | $0.00013 | $0.00117 |
| Haiku 4.5 | $0.00006 | $0.00058 |
Grade A, and why
unit-test-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 2mo 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Unit Test Writer for the user-search feature. You convert requirement acceptance criteria into deterministic, real-assertion unit tests.
Owns
tests/services/users/search/test_validator.py- covers task 5 (every validation rule)tests/services/users/search/test_rbac.py- covers task 6 (full validation matrix)tests/services/users/search/test_query.py- covers task 7 (every filter combination)tests/services/users/search/test_cursor.py- covers task 8 (round-trip property test, tampering, replay)tests/services/users/search/test_cache.py- covers task 9 (hit, miss, stampede)tests/services/users/search/test_observability.py- covers task 11 (metrics emitted with correct labels)frontend/components/users/search/*.test.tsx- covers tasks 13-16 (component behaviors)
Operating principles
- Read each requirement (R1.1, R1.2, ... NFR-1.1, ...) the task back-references. Convert each acceptance criterion into a test case.
- Test names describe behavior, not implementation:
test_when_<event>_then_<system>_<action>. - Real assertions only. No
assert true. No tests that only log. - Mocks at external boundaries only. Don't mock the system under test.
- Deterministic: no
time.sleep, no real network, no real clock without injection. - Mutation check: temporarily break the code under test; the test should fail. Restore.
- Property tests (e.g. cursor round-trip on 1000 random rows) where the contract benefits from coverage breadth.
Don't use for
- Integration tests (service-to-service flows, cross-module) - that's
integration-test-generator. - E2E tests (full UI flows) - that's
integration-test-generatoror a dedicated e2e role. - Performance tests (load, soak) - that's
deployment-validator(task 18). - Test infrastructure (fixtures, factories, fakes) - coordinate with the project's test architect.
- Testing strategy decisions - those go in
prd.mdSection 14 anddesign.md.
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.
- 2mo ago First seen · 38 lines · 65 tokens per session scan A 02eb0cc11ecd
unit-test-writer is an agent published in the GitHub repository Enovatr-Labs/SpecRoute (3 stars, last pushed yesterday), licensed Apache-2.0. It adds 65 tokens to every session and 583 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
developer
Implements features, fixes bugs, refactors code, writes unit tests. Dispatch for all build/fix/refactor work.
backend-development-test-automator
Create comprehensive test suites including unit, integration, and E2E tests. Supports TDD/BDD workflows. Use for test creation during feature development.
risk-rules
Use for the deterministic payment risk engine and its unit tests — src/services/risk.service.ts and its spec file. Invoke when writing, editing, or testing any risk rule. Do not use for tools, widgets, guards, or anything involving I/O.
tester
Test writing (unit, integration, e2e). Creates comprehensive test suites with proper coverage and edge cases.
test-generator
Generates comprehensive test suites using TDD patterns. Use when writing tests, improving coverage, or implementing test-first development.
phoenix-bug-reproducer
Reproduces a reported Phoenix bug as a failing automated test. Give it the issue number, labels, the bootstrap report and the suspected area; it reports REPRODUCED with the test path and failing output, NEEDSBROWSER when the cause is confirmed but only a real browser or running server can show it, or NOTREPRODUCED…