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/jvidalv/mv-ignited/agents-mdgit clone --depth 1 https://github.com/jvidalv/mv-ignitedWrote 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/jvidalv/mv-ignited/agents-md)<a href="https://agentmods.dev/instructions/jvidalv/mv-ignited/agents-md"><img src="https://agentmods.dev/badge/instructions/jvidalv/mv-ignited/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 | $0.01867 | $0.01867 |
| Opus 5 | $0.00933 | $0.00933 |
| Sonnet 5 | $0.00373 | $0.00373 |
| Haiku 4.5 | $0.00187 | $0.00187 |
Grade A, and why
mv-ignited 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.
How it starts
The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to AI agents working with code in this repository.
Project Context
MV-Ignited is a browser extension that enhances the mediavida.com forum. It injects React components into the forum's existing DOM to add new features and improve the user experience.
Quick Start
yarn install # Install dependencies
yarn watch # Start development mode (outputs to dist/)
yarn build:chrome # Production build for Chrome → dist-chrome/
yarn build:chrome:zip # Build Chrome + create store-ready zip
yarn build:firefox # Production build for Firefox → dist-firefox/
yarn build:firefox:zip # Build Firefox + create store-ready zip
# Load dist/ (dev) or dist-chrome/ (prod) as unpacked extension in Chrome
Code Quality Validation
CRITICAL: After completing EVERY task, you MUST run these three commands:
yarn tsc --noEmit # Type checking
yarn eslint src --ext .ts,.tsx # Linting
yarn style # Formatting
Never skip this validation step. All three commands must pass before committing any changes.
Architecture Overview
Four Entry Points:
- Theme Loader (
src/theme-loader.ts) - Runs atdocument_startto inject custom theme CSS before any rendering - Background Service Worker (
src/background.ts) - Handles extension lifecycle, icon updates, and script injection - Popup UI (
src/popup.tsx) - Quick access settings interface - Content Scripts (
src/injected/) - Main functionality injected into forum pages
Key Directories:
src/domains/- Data parsing from forum DOM (pure functions)src/injected/- Injection orchestration and page detectionsrc/react/- React components for UI enhancementssrc/utils/- Zustand stores with localStorage persistence
State Management
Uses Zustand with subscribeWithSelector middleware and localStorage persistence:
// Main store: useStore
- threadsIgnored: string[]
- features: Feature[]
- users: MVUser[]
- customFont?: string
// Theme store: useCustomTheme
- customWidth, headerColour, pageBackground, primaryColour
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.
- 4d ago First seen · 214 lines · 1,867 tokens per session scan A c8ab220f88ee
mv-ignited AGENTS.md is an instructions file published in the GitHub repository jvidalv/mv-ignited (5 stars, last pushed 9mo ago), licensed MIT. It adds 1,867 tokens to every session, about $0.0093 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
browser-control-mcp CLAUDE.md
Instructions for eyalzh/browser-control-mcp, covering claude.md, commands, installation, build and individual project builds.
peerd AGENTS.md
AGENTS.md instructions for NotASithLord/peerd, covering agents.md — peerd, what peerd is, the codebase is five modules, what to read, in order and non-negotiable conventions.
teak AGENTS.md
AGENTS.md instructions for praveenjuge/teak, covering teak agent guide, start here, architecture invariants, convex work and verification.
recap AGENTS.md
Instructions for atliq/recap, covering agents.md, what recap is, setup & run, pip - simple fallback and testing.
campus-copilot AGENTS.md
AGENTS.md instructions for xiaojiou176-open/campus-copilot, covering campuscopilot repo agent notes, 先接受的事实, 当前正式主线, 绝对不要写偏的地方 and 当前事实层和展示层.
espai AGENTS.md
Instructions for pouriya/espai, covering agent guidelines, kept plain, generic primitives, never site adapters, never write to stdout and how chrome starts and kills this process.