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/main-optimizedgit 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 | $0.02116 |
| Opus 5 | $0.00000 | $0.01058 |
| Sonnet 5 | $0.00000 | $0.00423 |
| Haiku 4.5 | $0.00000 | $0.00212 |
Grade A, and why
main-optimized 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 today.
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:
- main-optimized — 100% identical, 0 lines differ
- main-optimized — 100% identical, 0 lines differ
- main-optimized — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🔍 OPTIMIZED MEMORY BANK SYSTEM
🚨 CRITICAL RULE: MEMORY BANK CREATION IS MANDATORY 🚨 Memory Bank MUST be created BEFORE any other operation in ANY mode NO process can continue without verifying Memory Bank existence
TL;DR: This system uses optimized context management and adaptive rule loading to maximize token efficiency while preserving the structured development approach.
🧭 OPTIMIZED MODE ARCHITECTURE
graph TD
subgraph "Memory Bank Core"
Context["Context Manager"]
Rules["Rule Loader"]
FileIO["File Manager"]
Transition["Mode Transition"]
end
subgraph "Custom Modes"
VAN["VAN<br>Initialization"]
PLAN["PLAN<br>Planning"]
CREATIVE["CREATIVE<br>Design"]
IMPLEMENT["IMPLEMENT<br>Building"]
REFLECT["REFLECT<br>Review"]
ARCHIVE["ARCHIVE<br>Documentation"]
end
Context --> VAN & PLAN & CREATIVE & IMPLEMENT & REFLECT & ARCHIVE
Rules --> VAN & PLAN & CREATIVE & IMPLEMENT & REFLECT & ARCHIVE
FileIO --> VAN & PLAN & CREATIVE & IMPLEMENT & REFLECT & ARCHIVE
Transition --> VAN & PLAN & CREATIVE & IMPLEMENT & REFLECT & ARCHIVE
VAN --> PLAN
PLAN --> CREATIVE
CREATIVE --> IMPLEMENT
IMPLEMENT --> REFLECT
REFLECT --> ARCHIVE
style Context fill:#4da6ff,stroke:#0066cc,color:white
style Rules fill:#ffa64d,stroke:#cc7a30,color:white
style FileIO fill:#4dbb5f,stroke:#36873f,color:white
style Transition fill:#d94dbb,stroke:#a3378a,color:white
📈 ADAPTIVE COMPLEXITY MODEL
graph TD
Task["Task Creation"] --> Complexity{"Complexity<br>Level?"}
Complexity -->|"Level 1<br>Quick Fix"| L1["3-Phase<br>Streamlined Process"]
Complexity -->|"Level 2<br>Enhancement"| L2["4-Phase<br>Balanced Process"]
Complexity -->|"Level 3<br>Feature"| L3["5-Phase<br>Comprehensive Process"]
Complexity -->|"Level 4<br>Enterprise"| L4["6-Phase<br>Governance Process"]
L1 --> L1_Process["VAN → IMPLEMENT → REFLECT"]
L2 --> L2_Process["VAN → PLAN → IMPLEMENT → REFLECT"]
L3 --> L3_Process["VAN → PLAN → CREATIVE → IMPLEMENT → REFLECT"]
L4 --> L4_Process["VAN → PLAN → CREATIVE → IMPLEMENT → REFLECT → ARCHIVE"]
style Complexity fill:#d94dbb,stroke:#a3378a,color:white
style L1 fill:#4dbb5f,stroke:#36873f,color:white
style L2 fill:#ffa64d,stroke:#cc7a30,color:white
style L3 fill:#4da6ff,stroke:#0066cc,color:white
style L4 fill:#ff5555,stroke:#cc0000,color:white
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.
- today First seen · 237 lines · 0 tokens per session scan A f2ef9192a426
main-optimized 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 2,116 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
cursorrules
CLAUDE.md.
telegram-bot-tests
Test conventions for Telegram Bot library.
1c-coding-standards
Стандарты кода BSL: именование, запросы, коллекции.
1c-skd-two-pass-preprocessing
Двухпроходный СКД: предобработка детальных записей до свертки.
model-selection
Стратегия выбора моделей: Opus/Sonnet/Haiku по типу задачи.
zpa-dependency-chain
ZPA application onboarding requires resources to be created in a specific dependency order. Skipping dependencies causes cryptic 400 errors.