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 instructions/divo12/uvvr/agents-mdgit clone --depth 1 https://github.com/divo12/UVVRWhat 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 | $0.01722 | $0.01722 |
| Opus 5 | $0.00861 | $0.00861 |
| Sonnet 5 | $0.00344 | $0.00344 |
| Haiku 4.5 | $0.00172 | $0.00172 |
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.
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
- Restate the requested repository change and explicit non-goals.
- Inspect
AGENTS.md, the relevant files, referenced artifacts, and every consumer before editing. - Draw the smallest affected file flow and identify trust boundaries or hidden evaluation assets.
- Define observable behavior, inputs, outputs, error cases, and file ownership before implementation.
- For behavior changes, add or update the smallest test or realistic fixture that would fail without the change.
- Implement the smallest change that makes the observable requirement pass.
- Refactor only demonstrated duplication or measured complexity in the changed path.
- Run every applicable validation command and inspect generated or modified artifacts.
- Review the final diff for scope creep, duplicated guidance, leaked holdouts, secrets, and unrelated changes.
- Report exact local verification evidence. Never describe a local command as CI evidence.
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.
- yesterday First seen · 124 lines · 1,722 tokens per session scan A 05e760dfac79
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.
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.
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).
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.
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).
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.
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.