You are an AI coding agent working with the Argus design intelligence platform. When connected to the Argus MCP server, you have access to design intelligence tools that let you analyze and improve visual quality. These tools return structured, deterministic results — not opinions. Input: { url?: string, selector?: string, html?: string } Output: PageSnapshot with element positions, computed styles, accessibility data, and structural relationships. Use this when you need to understand what's visually happening on a page before making…
This file tells AI coding agents how to work on the Argus codebase. Argus is a design intelligence runtime for AI agents. It gives coding agents the ability to see, judge, and learn from visual design quality. The codebase is a TypeScript monorepo using pnpm workspaces. protocol is the leaf dependency. Everything depends on it. Nothing depends on cli, mcp-server, or gateway — they are entry points.
Bring engineering, design, research, marketing, and sales onto the same page and keep them there. Covers alignment levels, RACI clarity, and continuous maintenance. Use when teams have different understandings of what's being built, cross-team dependencies are causing problems, or alignment keeps breaking down.
Get buy-in and drive alignment when you have no direct power over the people you need to move. Covers stakeholder framing, pre-wiring decisions, and building credibility over time. Use when pushing for a direction without exec authority, navigating disagreements, or when a proposal keeps getting blocked.
Build a productive relationship with leadership by communicating effectively, managing expectations, and knowing when to push back. Use when navigating executive relationships, seeking alignment on direction, or when leadership requests conflict with team capacity.
Partner with design to create better products, not just prettier ones. Covers when to involve design, how to give useful feedback, and respecting the design process. Use when PM-design handoffs feel clunky, design feedback conversations are unproductive, or design is brought in too late.
Partner with engineering as a collaborator, not a ticket-writer. Covers communication norms, technical empathy, scope negotiation, and building mutual trust. Use when PM-engineering relationships feel transactional, technical decisions are made without product input, or scope conversations become adversarial.
Partner with marketing, sales, and customer success to bring products to market effectively. Covers launch coordination, sales enablement, and feedback loops. Use when launches aren't driving adoption, sales can't articulate the value prop, or customer feedback isn't reaching the product team.
Ship updates people actually want to read. Structures release notes, changelog entries, and product updates with what-changed, why-it-matters, and what-to-do-next. Use when writing changelogs or release announcements.
Write headlines, CTAs, and value props that move people to act. Audits existing copy for weak verbs, vague claims, and missing specificity. Use when writing landing pages, hero sections, email subject lines, or any surface where words need to do real work.
The small words that shape big experiences. Button labels, tooltips, confirmations, placeholders, and the 3-word strings that determine whether a product feels polished or half-finished. Use during any copy audit pass.
Tell the product story in a way that sticks. Structures origin stories, problem narratives, and transformation arcs. Use when building about pages, launch announcements, or pitch decks.
Create structured competitive battlecards for sales, product, and strategy conversations. Covers positioning, objection handling, competitive landmines, and knowing when to walk away. Use when preparing for competitive deals, losing to a specific competitor, or entering a market with established players.
Identify and prioritize feature gaps between your product and competitors. Not just what's missing but which gaps matter, which don't, and which you should intentionally keep. Use when losing deals to missing features, planning roadmap with competitive context, or evaluating build-buy-partner decisions.
Analyze the real cost of switching between products — financial, technical, operational, political, and emotional. Use when trying to win customers from competitors, worried about churn to alternatives, designing migration tools, or setting pricing relative to switching friction.
Design calls-to-action that people actually click. Covers button copy, placement logic, urgency without manipulation, and progressive commitment. Use when reviewing pages for conversion potential or when CTA copy feels generic.
Reduce abandonment in every form, signup, and checkout flow. Multi-step logic, field reduction, inline validation, and completion micro-copy. Use when building signup flows, checkout pages, or any multi-field input.
Information architecture that guides visitors from curiosity to commitment. Enforces section order, content hierarchy, and scroll-depth logic. Use when building landing pages, product pages, or any conversion surface.
Present pricing in ways that reduce friction and increase clarity. Handles tier naming, feature comparison, anchor pricing, and plan selection psychology. Use when designing pricing pages, plan selectors, or upgrade prompts.
Build credibility through evidence, not claims. Patterns for social proof, testimonials, logo walls, case studies, and security badges. Use when conversion is low despite good traffic or when the product is new and unknown.
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
Dragoon0xAGENTS.md