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/rule-calling-guidegit clone --depth 1 https://github.com/bia-technologies/yaxunitWrote 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/bia-technologies/yaxunit/rule-calling-guide)<a href="https://agentmods.dev/rules/bia-technologies/yaxunit/rule-calling-guide"><img src="https://agentmods.dev/badge/rules/bia-technologies/yaxunit/rule-calling-guide.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 | $0.00639 |
| Opus 5 | $0.00000 | $0.00319 |
| Sonnet 5 | $0.00000 | $0.00128 |
| Haiku 4.5 | $0.00000 | $0.00064 |
Grade A, and why
rule-calling-guide 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 2d 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.
Copies of this mod
3 near-identical copies found in the catalogue:
- rule-calling-guide — 100% identical, 0 lines differ
- rule-calling-guide — 100% identical, 0 lines differ
- rule-calling-guide — 100% identical, 0 lines differ
What it actually says
VAN QA: COMPREHENSIVE RULE CALLING GUIDE
TL;DR: This reference guide shows how to properly call all VAN QA rules at the right time during the validation process.
🔍 RULE CALLING BASICS
Remember these key principles:
- Always use the
fetch_rulestool to load rules - Use exact rule paths
- Load components only when needed
📋 MAIN QA ENTRY POINT
When user types "VAN QA", load the main entry point:
fetch_rules with "isolation_rules/visual-maps/van-qa-main"
📋 VALIDATION CHECKS
Load these components sequentially during validation:
1. fetch_rules with "isolation_rules/visual-maps/van-qa-checks/dependency-check"
2. fetch_rules with "isolation_rules/visual-maps/van-qa-checks/config-check"
3. fetch_rules with "isolation_rules/visual-maps/van-qa-checks/environment-check"
4. fetch_rules with "isolation_rules/visual-maps/van-qa-checks/build-test"
📋 UTILITY COMPONENTS
Load these when needed based on validation results:
- For reports: fetch_rules with "isolation_rules/visual-maps/van-qa-utils/reports"
- For fixes: fetch_rules with "isolation_rules/visual-maps/van-qa-utils/common-fixes"
- For transitions: fetch_rules with "isolation_rules/visual-maps/van-qa-utils/mode-transitions"
⚠️ CRITICAL REMINDERS
Remember to call these rules at these specific points:
- ALWAYS load the main QA entry point when "VAN QA" is typed
- ALWAYS load dependency-check before starting validation
- ALWAYS load reports after completing validation
- ALWAYS load mode-transitions after successful validation
- ALWAYS load common-fixes after failed validation
🔄 FULL VALIDATION SEQUENCE
Complete sequence for a QA validation process:
- Load main entry:
isolation_rules/visual-maps/van-qa-main - Load first check:
isolation_rules/visual-maps/van-qa-checks/dependency-check - Load second check:
isolation_rules/visual-maps/van-qa-checks/config-check - Load third check:
isolation_rules/visual-maps/van-qa-checks/environment-check - Load fourth check:
isolation_rules/visual-maps/van-qa-checks/build-test - If pass, load:
isolation_rules/visual-maps/van-qa-utils/reports - If pass, load:
isolation_rules/visual-maps/van-qa-utils/mode-transitions - If fail, load:
isolation_rules/visual-maps/van-qa-utils/common-fixes
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.
- 2d ago First seen · 66 lines · 0 tokens per session scan A aeae1e80bd34
rule-calling-guide 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 639 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
telegram-bot-tests
Test conventions for Telegram Bot library.
testing
Testing conventions for Ion Design System using Jest and Angular Testing Library.
1c-coding-standards
Стандарты кода BSL: именование, запросы, коллекции.
unit-testing-standards
Cursor rule "unit-testing-standards" from adobecom/da-express-milo, covering unit testing standards, testing philosophy, testing framework stack, test structure patterns and 1. standard test file organization.
testing
Guide for writing pytest unit and integration tests.
testing
Testing with @iobroker/testing and Mocha.