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/ni032mas/agent-skills-ruWrote 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/ni032mas/agent-skills-ru/rule)<a href="https://agentmods.dev/rules/ni032mas/agent-skills-ru/rule"><img src="https://agentmods.dev/badge/rules/ni032mas/agent-skills-ru/rule/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/rules/ni032mas/agent-skills-ru/rule"><img src="https://agentmods.dev/badge/rules/ni032mas/agent-skills-ru/rule.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 | $0.00000 | $0.00362 |
| Opus 5.5 | $0.00000 | $0.00145 |
| Sonnet 5.5 | $0.00000 | $0.00072 |
| Haiku 4.5 | $0.00000 | $0.00036 |
Grade A, and why
rule 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 2mo 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
Russian Legal Contract Review
Use this rule when the task mentions Russian law, ГК РФ, 152-ФЗ, 149-ФЗ, РКН, Роскомнадзор, персональные данные, договор, оферта, NDA, SaaS, license, marketplace terms, privacy policy, or consent text.
Follow the canonical workflow in skills/ru-legal-contract-review/SKILL.md if the repository contains it. If not, apply these essentials:
- Verify current law before current legal conclusions; cite source URL, act name/number, article/clause, and edition/effective date.
- Ask or infer our side: customer/vendor, buyer/seller, licensor/licensee, operator/processor, B2B/B2C.
- Check completeness: parties, authority, subject matter, price/VAT, acceptance, exhibits, signatures, personal-data terms, IP, termination, liability, venue.
- For personal data, check 152-ФЗ lawful basis, RKN notification, localization, cross-border transfer, processors, consents, privacy policy, breach duties, and security owner.
- Treat
143-ФЗin a RKN/personal-data context as ambiguous; clarify whether the user means 149-ФЗ, 152-ФЗ, 242-ФЗ, or a specific 143-ФЗ. - Do not invent court practice, article numbers, or regulator positions.
- Output: short conclusion, blockers, risk table, ready-to-paste rewrites, questions before signing, sources.
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.
- 2mo ago First seen · 23 lines · 0 tokens per session scan A 1a0e127b68d7
rule is a cursor rule published in the GitHub repository ni032mas/agent-skills-ru (6 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 362 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 2026-08-31.
Other cursor rules, from other repositories
leanctx-ip-governance
LeanCTX Context Gateway source/decision scope, Apache IP and private EE safety gate for all coding, docs and releases.
tell-demo-narrative
Hackathon demo narrative and rules compliance.
qubiton-lifecycle
Enforces correct QubitOn MCP tool lifecycle, safety rules, and error handling. Governs all interactions with the QubitOn MCP server.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.