frameproof AGENTS.md

frameproof AGENTS.md is an instructions file for Codex, OpenCode from edvardgrishin27/frameproof. It costs 334 tokens per session, scanned A, original, MIT.

Instructions for Frameproof, an offline tool that examines videos and answers questions about their contents with time and frame references. It uses local video downloading, processing, and transcription tools, so API keys are not required.

In plain words
What is it for?
Inspecting videos, answering questions about visible content, adding timestamps and frame numbers to findings, and checking those references.
Why use it?
It prevents unsupported claims about what appears in a video by requiring every screen-related statement to point to a verifiable moment.

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/edvardgrishin27/frameproof/agents-md
Clone the repo
git clone --depth 1 https://github.com/edvardgrishin27/frameproof

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for frameproof AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/edvardgrishin27/frameproof/agents-md.svg)](https://agentmods.dev/instructions/edvardgrishin27/frameproof/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/edvardgrishin27/frameproof/agents-md"><img src="https://agentmods.dev/badge/instructions/edvardgrishin27/frameproof/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 334 This file is loaded in full into every session.
When invoked 334 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 $0.00334 $0.00334
Opus 5 $0.00167 $0.00167
Sonnet 5 $0.00067 $0.00067
Haiku 4.5 $0.00033 $0.00033

Measured 4d ago against content hash d6f4d36277f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

frameproof 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 4d 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.

AGENTS.md · 31 lines

What it actually says

frameproof

Смотрит видео и отвечает на вопросы по нему без слепых зон, с обязательной ссылкой на момент. Полностью офлайн: yt-dlp + ffmpeg + локальная расшифровка, ключи не нужны.

Полная инструкция для агента — в skills/frameproof/SKILL.md.

Установка

pip install git+https://github.com/edvardgrishin27/frameproof
frameproof doctor      # что есть в системе
frameproof install     # скилл и проверяющий в Claude Code

Для других хостов (Codex, Cursor, Copilot и прочие, кто понимает Agent Skills):

npx skills add edvardgrishin27/frameproof -g

Работа вне Claude Code нами не проверялась. Формат SKILL.md переносим, но заявлять поддержку без живой проверки мы не будем — см. CLAIMS.md.

Одно правило, которое нельзя обходить

Никогда не утверждай, что было на экране, не увидев кадра. Каждое утверждение об экране — с меткой [MM:SS / fNNNN]. Метка проверяема: frameproof verify <разбор.md> --out <индекс> поймает выдуманный кадр, разъехавшийся тайм-код и цитату, которой на экране нет.

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. 4d ago First seen · 31 lines · 334 tokens per session scan A d6f4d36277f3

Subscribe to this mod's changes

frameproof AGENTS.md is an instructions file published in the GitHub repository edvardgrishin27/frameproof (24 stars, last pushed yesterday), licensed MIT. It adds 334 tokens to every session, about $0.0017 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 2026-08-30.