What is unflick AGENTS.md?

A project instruction file for unflick, a video player for Windows and macOS with a graphical interface, command-line controls, and an AI connection.

It is for guiding development of unflick and keeping its generated AGENTS.md instructions consistent with the source file.

It gives coding agents clear rules for building features in the shared Rust core and checking them through the command line and AI interface before adding the graphical layer.

How zhitongblog/unflick configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to zhitongblog/unflick. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/zhitongblog/unflick/master/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/zhitongblog/unflick

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/zhitongblog/unflick/agents-md/github.svg)](https://agentmods.dev/instructions/zhitongblog/unflick/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/zhitongblog/unflick/agents-md"><img src="https://agentmods.dev/badge/instructions/zhitongblog/unflick/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/zhitongblog/unflick/agents-md"><img src="https://agentmods.dev/badge/instructions/zhitongblog/unflick/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 6,431 This file is loaded in full into every session.

When invoked 6,431 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.06431	$0.06431
Opus 5.5	$0.02572	$0.02572
Sonnet 5.5	$0.01286	$0.01286
Haiku 4.5	$0.00643	$0.00643

Measured 1mo ago against content hash bb97292a3e44, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

unflick 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 1mo 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 · 538 lines

How it starts

The opening of the file, as written. The whole thing — 538 lines — stays where its author put it; the contents beside it link to each section on GitHub.

unflick

A modern, beautiful, AI-ready video player for Windows and macOS.

AGENTS.md is generated from this file by scripts/gen-agents.sh — the two say the same thing and differ only in which agent they name. Edit here, then run the script; CI fails if they drift.

Project Overview

unflick is a cross-platform video player that provides three interfaces:

GUI — Modern UI for regular users (React + TypeScript + Tailwind)
CLI — Command-line control for power users and scripts
MCP Server — AI agent integration via Model Context Protocol

All three interfaces share a unified Rust core.

Core Constraint: CLI/MCP First

Every feature MUST be fully functional via CLI and MCP before it is considered complete.

This is non-negotiable. The development loop is:

Build the Rust core logic
Expose it via CLI command + MCP tool
Self-test through CLI/MCP (the agent can verify its own work)
Only then build the GUI layer on top

A feature without CLI/MCP coverage does NOT ship. The first usable release (v0.1) must be 100% operable through CLI and MCP — GUI is a bonus, not a requirement for v0.1.

Why

The agent can self-test every feature during development via CLI and MCP
Ensures the Rust core is clean and decoupled from any UI
CLI/MCP users get first-class support, not an afterthought
Forces good architecture: if it works headless, the GUI is just a skin

Self-Test Protocol

After implementing any feature, the agent MUST verify it by:

Running the CLI command and checking stdout/exit code
Calling the MCP tool and validating the JSON response
If either fails, fix before moving on — do NOT defer to "test later"
Adding a case to src-tauri/tests/ — a verification that lives only in a chat transcript is gone the moment the session ends

Test suite

Read the full file on GitHub · 538 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.

1mo ago Changed · +6 lines · +136 tokens per session bb97292a3e44
1mo ago Changed · +3 lines · +56 tokens per session 39bf0d30873b
1mo ago First seen · 529 lines · 6,239 tokens per session scan A bb3459437eb5

Subscribe to this mod's changes

unflick AGENTS.md is an instructions file published in the GitHub repository zhitongblog/unflick (1 stars, last pushed 1mo ago), licensed MIT. It adds 6,431 tokens to every session, about $0.0257 per session on Opus 5.5. 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 2026-09-17.

unflick AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
unflick AGENTS.mdzhitongblog/unflick	Instructions file	1	1mo ago	MIT	A	6,431	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

unflick: Instructions file for Codex