uvvr

A rule for designing evaluations of AI results when the results are open-ended or only partly checkable. It directs the agent to follow the UVVR instructions.

In plain words
What is it for?
Use it when creating tests for generated text, plans, or other AI outcomes that require broader evaluation.
Why use it?
It helps assess AI work that cannot be judged with simple pass-or-fail checks.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/divo12/uvvr/uvvr
Clone the repo
git clone --depth 1 https://github.com/divo12/UVVR

Made for: Cursor.

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 82 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00016 $0.00082
Opus 5 $0.00008 $0.00041
Sonnet 5 $0.00003 $0.00016
Haiku 4.5 $0.00002 $0.00008

Measured yesterday against content hash 0a9b1a372494, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

uvvr 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.

.cursor/rules/uvvr.mdc · 9 lines

What it actually says

When this rule applies, read skills/uvvr/SKILL.md completely and follow it as the source of truth. Resolve its referenced assets and references relative to skills/uvvr/. Do not duplicate or reinterpret the UVVR workflow in this rule.

Changes

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.

  1. yesterday First seen · 9 lines · 16 tokens per session scan A 0a9b1a372494

Subscribe to this mod's changes

uvvr is a cursor rule published in the GitHub repository divo12/UVVR (2 stars, last pushed 2d ago), licensed MIT. It adds 16 tokens to every session and 82 once invoked, about $0.0001 per session on Opus 5. 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.