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/alkoleft/platform-context-exporter/van-qa-maingit clone --depth 1 https://github.com/alkoleft/platform-context-exporterWrote 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/rules/alkoleft/platform-context-exporter/van-qa-main)<a href="https://agentmods.dev/rules/alkoleft/platform-context-exporter/van-qa-main"><img src="https://agentmods.dev/badge/rules/alkoleft/platform-context-exporter/van-qa-main.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.01404 |
| Opus 5 | $0.00000 | $0.00702 |
| Sonnet 5 | $0.00000 | $0.00281 |
| Haiku 4.5 | $0.00000 | $0.00140 |
Grade A, and why
van-qa-main 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.
This is a copy
100% identical to van-qa-main — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VAN MODE: QA TECHNICAL VALIDATION (Main Entry)
TL;DR: This is the entry point for the QA validation process that executes after CREATIVE mode and before BUILD mode. It ensures technical requirements are met before implementation begins.
📣 HOW TO USE THESE QA RULES
To access any QA validation rule or component, use the fetch_rules tool with exact rule names:
// CRITICAL: Always use fetch_rules to load validation components
// For detailed examples and guidance, load:
// isolation_rules/visual-maps/van-qa-utils/rule-calling-guide
🚀 VAN QA MODE ACTIVATION
After completing CREATIVE mode, when the user types "VAN QA", respond:
graph TD
UserQA["User Types: QA"] --> HighPriority["⚠️ HIGH PRIORITY COMMAND"]
HighPriority --> CurrentTask["Pause Current Task/Process"]
CurrentTask --> LoadQA["Load QA Main Map (This File)"]
LoadQA --> RunQA["Execute QA Validation Process"]
RunQA --> QAResults{"QA Results"}
QAResults -->|"PASS"| ResumeFlow["Resume Prior Process Flow"]
QAResults -->|"FAIL"| FixIssues["Fix Identified Issues"]
FixIssues --> ReRunQA["Re-run QA Validation"]
ReRunQA --> QAResults
style UserQA fill:#f8d486,stroke:#e8b84d,color:black
style HighPriority fill:#ff0000,stroke:#cc0000,color:white,stroke-width:3px
style LoadQA fill:#4da6ff,stroke:#0066cc,color:white
style RunQA fill:#4da6ff,stroke:#0066cc,color:white
style QAResults fill:#f6546a,stroke:#c30052,color:white
QA Interruption Rules
- Immediate Precedence:
QAcommand interrupts everything. - Load & Execute: Load this map (
van-qa-main.mdc) and its components (see below). - Remediation Priority: Fixes take priority over pending mode switches.
- Resume: On PASS, resume the previous flow.
⚠️ QA OVERRIDE ACTIVATED
All other processes paused
QA validation checks now running...
Any issues found MUST be remediated before continuing with normal process flow
🔍 TECHNICAL VALIDATION OVERVIEW
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 · 142 lines · 0 tokens per session scan A 76548d715d07
van-qa-main is a cursor rule published in the GitHub repository alkoleft/platform-context-exporter (48 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,404 tokens. A static security scan graded it A with 0 findings. It is 100% identical to van-qa-main, differing in 0 lines, and is treated as a copy.
Other cursor rules, from other repositories
bsl-ssl
Переиспользование БСП, разметка правок типовых модулей, устаревшие объекты.
edt-form-xml-requirements
Требования EDT к XML-формам (Form.form): extInfo, дефолты полей.
1c-report-direct-query
Прямой запрос в отчётах 1С (СКД) без схемы компоновки.
query-optimization-tips
Оптимизация запросов 1С: ВЫРАЗИТЬ, ВТ, индексы.
1c-mdo-integrity
Целостность MDO-файлов: UUID, ссылки.
1c-skd-two-pass-preprocessing
Двухпроходный СКД: предобработка детальных записей до свертки.