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.
npx agentmods add rules/bia-technologies/yaxunit/build-testgit clone --depth 1 https://github.com/bia-technologies/yaxunitWhat 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 | $0.00000 | $0.00877 |
| Opus 5 | $0.00000 | $0.00439 |
| Sonnet 5 | $0.00000 | $0.00175 |
| Haiku 4.5 | $0.00000 | $0.00088 |
Grade A, and why
build-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 yesterday.
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.
Copies of this mod
4 near-identical copies found in the catalogue:
- build-test — 100% identical, 0 lines differ
- build-test — 100% identical, 0 lines differ
- build-test — 100% identical, 0 lines differ
- build-test — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VAN QA: MINIMAL BUILD TEST
TL;DR: This component performs a minimal build test to ensure core build functionality works properly.
4️⃣ MINIMAL BUILD TEST PROCESS
graph TD
Start["Minimal Build Test"] --> CreateTest["Create Minimal<br>Test Project"]
CreateTest --> BuildTest["Attempt<br>Build"]
BuildTest --> BuildStatus{"Build<br>Successful?"}
BuildStatus -->|"Yes"| RunTest["Run Basic<br>Functionality Test"]
BuildStatus -->|"No"| FixBuild["Fix Build<br>Issues"]
FixBuild --> RetryBuild["Retry Build"]
RetryBuild --> BuildStatus
RunTest --> TestStatus{"Test<br>Passed?"}
TestStatus -->|"Yes"| TestSuccess["Minimal Build Test<br>✅ PASS"]
TestStatus -->|"No"| FixTest["Fix Test<br>Issues"]
FixTest --> RetryTest["Retry Test"]
RetryTest --> TestStatus
style Start fill:#4da6ff,stroke:#0066cc,color:white
style TestSuccess fill:#10b981,stroke:#059669,color:white
style BuildStatus fill:#f6546a,stroke:#c30052,color:white
style TestStatus fill:#f6546a,stroke:#c30052,color:white
Minimal Build Test Implementation:
# Example: Perform minimal build test for a React project
function Perform-MinimalBuildTest {
$buildSuccess = $false
$testSuccess = $false
# Create minimal test project
$testDir = ".__build_test"
if (Test-Path $testDir) {
Remove-Item -Path $testDir -Recurse -Force
}
try {
# Create minimal test directory
New-Item -Path $testDir -ItemType Directory | Out-Null
Push-Location $testDir
# Initialize minimal package.json
@"
{
"name": "build-test",
"version": "1.0.0",
"description": "Minimal build test",
"main": "index.js",
"scripts": {
"build": "echo Build test successful"
}
}
"@ | Set-Content -Path "package.json"
# Attempt build
npm run build | Out-Null
$buildSuccess = $true
# Create minimal test file
@"
console.log('Test successful');
"@ | Set-Content -Path "index.js"
# Run basic test
node index.js | Out-Null
$testSuccess = $true
} catch {
Write-Output "❌ Build test failed: $($_.Exception.Message)"
} finally {
Pop-Location
if (Test-Path $testDir) {
Remove-Item -Path $testDir -Recurse -Force
}
}
# Display results
if ($buildSuccess -and $testSuccess) {
Write-Output "✅ Minimal build test passed successfully"
return $true
} else {
if (-not $buildSuccess) {
Write-Output "❌ Build process failed"
}
if (-not $testSuccess) {
Write-Output "❌ Basic functionality test failed"
}
return $false
}
}
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.
- yesterday First seen · 117 lines · 0 tokens per session scan A 19bf082938ab
build-test is a cursor rule published in the GitHub repository bia-technologies/yaxunit (322 stars, last pushed 2mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 877 tokens. 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 2026-09-01.
Other cursor rules, from other repositories
ktnip-ksp-processor
KSP processor architecture, collectors, and codegen for ktnip.
1c-coding-standards
Стандарты кода BSL: именование, запросы, коллекции.
edt-form-xml-requirements
Требования EDT к XML-формам (Form.form): extInfo, дефолты полей.
async-methods-1c
Асинхронные методы 1С: Асинх/Ждать/Обещание (8.3.18+).
1c-skd-two-pass-preprocessing
Двухпроходный СКД: предобработка детальных записей до свертки.
1c-form-reserved-names
Зарезервированные имена свойств в модулях форм 1С.