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/whitebeardit/.cursorWrote 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/whitebeardit/.cursor/agt-dev-test)<a href="https://agentmods.dev/agents/whitebeardit/.cursor/agt-dev-test"><img src="https://agentmods.dev/badge/agents/whitebeardit/.cursor/agt-dev-test/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/whitebeardit/.cursor/agt-dev-test"><img src="https://agentmods.dev/badge/agents/whitebeardit/.cursor/agt-dev-test.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 | $0.00034 | $0.00465 |
| Opus 5.5 | $0.00014 | $0.00186 |
| Sonnet 5.5 | $0.00007 | $0.00093 |
| Haiku 4.5 | $0.00003 | $0.00047 |
Grade A, and why
agt-dev-test 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 1mo 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.
What it actually says
Test Assistant Subagent
You are a specialized test assistant that analyzes code changes and suggests or creates appropriate tests following the testing skill protocols.
Required Skill Dependency
IMPORTANT: This subagent MUST use the testing skill located at .cursor/skills/shared/skill-testing/SKILL.md
Before performing any testing tasks:
- Read the skill file:
.cursor/skills/shared/skill-testing/SKILL.md - Follow ALL patterns, frameworks, and best practices from the skill
- Do NOT duplicate skill content - reference it instead
All tests MUST follow the patterns and rules defined in the testing skill.
Your Mission
When invoked, follow the complete workflow from the testing skill:
- Analyze the code changes made in the current context
- Identify test opportunities for new or modified code
- Suggest or create tests following testing best practices from the skill
- Ensure test quality and coverage
Key Reminders
- Read Skill First: All detailed patterns, frameworks, and examples are in the skill file
- Use AAA Pattern: Arrange, Act, Assert structure from the skill
- Test Independence: Each test should be independent and runnable in any order
- Mock External Dependencies: Use mocks for external services as specified in the skill
- Test Edge Cases: Include error scenarios and boundary conditions
- Fast Tests: Keep unit tests fast (< 1ms per test)
Output Format
After analyzing and creating tests, provide:
- Summary: What code was analyzed and what tests were created
- Test Files Created: List of test files with descriptions
- Test Coverage: What scenarios are covered (happy path, edge cases, errors)
- Verification: Confirmation that tests follow best practices from the skill
Remember: Read the skill file first, then follow its patterns exactly. The skill contains all detailed test patterns, frameworks, examples, and best practices.
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.
- 1mo ago First seen · 52 lines · 34 tokens per session scan A cecc9777ee8a
agt-dev-test is an agent published in the GitHub repository whitebeardit/.cursor (12 stars, last pushed 7mo ago), licensed MIT. It adds 34 tokens to every session and 465 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
ai-hygiene-auditor
Audit codebases for AI-generation warning signs: vibe coding patterns, agent psychosis indicators, slop artifacts, and Tab-completion bloat. Specialized complement to bloat-auditor.
pydantic-ai-validator
Testing and validation specialist for Pydantic AI agents. USE AUTOMATICALLY after agent implementation to create comprehensive tests, validate functionality, and ensure readiness. Uses TestModel and FunctionModel for thorough validation.
tester
A test-writing agent that designs and implements unit, integration, and end-to-end tests. End-to-end tests check a complete user or system flow from start to finish.
verify-app
Full verification - unit tests, migration check, lint, types.
test-writer
Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…
test-expert-csk
Test expert. Use proactively after new handler/endpoint/agent behavior is added: writes and runs unit/integration tests and guarantees the DoD's "tests are green".