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/robspectre/mvf1/agents-mdgit clone --depth 1 https://github.com/RobSpectre/mvf1Wrote 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.
[](https://agentmods.dev/instructions/robspectre/mvf1/agents-md)<a href="https://agentmods.dev/instructions/robspectre/mvf1/agents-md"><img src="https://agentmods.dev/badge/instructions/robspectre/mvf1/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00601 | $0.00601 |
| Opus 5 | $0.00300 | $0.00300 |
| Sonnet 5 | $0.00120 | $0.00120 |
| Haiku 4.5 | $0.00060 | $0.00060 |
Grade A, and why
mvf1 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project
mvf1 is a Python library, CLI, and MCP server for controlling MultiViewer video players. It talks to the MultiViewer desktop app's GraphQL API at http://localhost:10101/api/graphql using sgqlc. The package is published on PyPI and runs on Python 3.10+.
Layout
mvf1/mvf1.py—MultiViewerForF1client andPlayermodelmvf1/mcp.py— FastMCP server exposing MultiViewer controls as MCP toolsmvf1/cmdline.py— Click CLI (players,player,mcpcommands)mvf1/mvf1_schema.py— auto-generated GraphQL schema (do not hand-edit)tests/— pytest tests usingunittest.TestCasestyle with mocksdocs/— Sphinx docstox.ini— test matrix for Python 3.10–3.13
Setup
pip install -e ./
Requires Python >= 3.10. Dependencies: click, sgqlc, fastmcp.
Commands
| Task | Command |
|---|---|
| Run tests (all Pythons) | tox |
| Run tests (current env) | pytest --cov=./ |
| Run a single test file | pytest tests/test_mvf1.py |
| CLI help | mvf1-cli --help |
| Start MCP server | mvf1-cli mcp |
| Start MCP with custom URL | mvf1-cli mcp --url http://<host>/api/graphql |
Conventions
- Tests use
unittest.TestCasewith@patch('sgqlc.endpoint.http.HTTPEndpoint.__call__')to mock GraphQL responses. - Test fixtures live in
tests/players.json. - CLI commands catch
URLError(MultiViewer not running) andMultiViewerForF1Error(GraphQL errors) and raiseclick.UsageError. - MCP tools in
mvf1/mcp.pywrapMultiViewerForF1client methods and are decorated with@mcp.tool(). - README mentions
blackbut no formatter/linter config files exist in the repo.
Pitfalls
- Player creation lag:
player_createis non-blocking; new players take 200–800 ms to appear in the API. Callers must delay before querying the new player. - Tests require no live server: all HTTP calls are mocked; do not hit
localhost:10101in tests. mvf1/mvf1_schema.pyis auto-generated; hand edits will be overwritten.
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.
- 3d ago First seen · 49 lines · 601 tokens per session scan A 6478f5578eb9
mvf1 AGENTS.md is an instructions file published in the GitHub repository RobSpectre/mvf1 (19 stars, last pushed 5d ago), licensed MIT. It adds 601 tokens to every session, about $0.0030 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.
Other instructions, from other repositories
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).
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.
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.
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.
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).
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.