UVVR AGENTS.md

Repository instructions for UVVR, a project that designs evaluations for AI systems when some results cannot be directly checked. They define the project’s terminology, boundaries, workflow, and implementation rules.

In plain words
What is it for?
Use them when changing UVVR’s code, evaluation-design skill, research artifacts, or repository structure.
Why use it?
They help coding agents avoid treating uncertain scores as proven truth and keep automated checks separate from human judgment.

Instructions file for CodexOpenCode

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 instructions/divo12/uvvr/agents-md
Clone the repo
git clone --depth 1 https://github.com/divo12/UVVR

Made for: Codex, OpenCode.

Per session 1,722 This file is loaded in full into every session.
When invoked 1,722 The same file — it is already loaded in full.
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 $0.01722 $0.01722
Opus 5 $0.00861 $0.00861
Sonnet 5 $0.00344 $0.00344
Haiku 4.5 $0.00172 $0.00172

Measured yesterday against content hash 05e760dfac79, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

UVVR AGENTS.md 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.

AGENTS.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UVVR Engineering Rules

These instructions apply to coding agents working anywhere in this repository.

Product boundaries

  • This repository develops an instruction-first Codex skill for designing defensible evals for AI systems whose work is partly unverifiable.
  • UVVR must distinguish deterministic or executable verification, grounded or anchored verification, calibrated semantic proxies, and human or delayed-outcome judgment.
  • Preserve the V4–V0 terminology defined in the research artifacts. Never implement behavior that labels an LLM score, rubric score, majority vote, or learned reward model as ground truth.
  • Preserve an explicit unverifiable remainder. Do not force every criterion into an automated score.
  • Keep intended outcomes separate from forbidden outcomes. Safety, permission, privacy, and evidence-integrity failures are gates.
  • The first product wedge is eval design for research agents. Customer support is the first out-of-domain contrast, not a second MVP domain.
  • The first milestone is one instruction-only skill plus real examples and behavioral evidence. Do not add hooks, persistent modes, MCP, dashboards, hosted services, or multi-host adapters without an observed need.

Required coding workflow

  1. Restate the requested repository change and explicit non-goals.
  2. Inspect AGENTS.md, the relevant files, referenced artifacts, and every consumer before editing.
  3. Draw the smallest affected file flow and identify trust boundaries or hidden evaluation assets.
  4. Define observable behavior, inputs, outputs, error cases, and file ownership before implementation.
  5. For behavior changes, add or update the smallest test or realistic fixture that would fail without the change.
  6. Implement the smallest change that makes the observable requirement pass.
  7. Refactor only demonstrated duplication or measured complexity in the changed path.
  8. Run every applicable validation command and inspect generated or modified artifacts.
  9. Review the final diff for scope creep, duplicated guidance, leaked holdouts, secrets, and unrelated changes.
  10. Report exact local verification evidence. Never describe a local command as CI evidence.

Read the full file on GitHub · 124 lines

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 · 124 lines · 1,722 tokens per session scan A 05e760dfac79

Subscribe to this mod's changes

UVVR AGENTS.md is an instructions file published in the GitHub repository divo12/UVVR (2 stars, last pushed 2d ago), licensed MIT. It adds 1,722 tokens to every session, about $0.0086 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.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens