convey copilot-instructions.md

Project instructions for Convey, a browser overlay, visual inspector, and MCP server for editing Tailwind CSS classes in a running React or Angular application. Tailwind CSS is a system for styling web pages with small reusable class names.

In plain words
What is it for?
Working on the overlay, inspector panel, WebSocket server, React or Angular integrations, Tailwind styling, tests, and Storybook components.
Why use it?
They give an AI agent the project's architecture, brand colors, coding rules, and testing conventions so changes fit the existing codebase.

Instructions file for GitHub Copilot

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/bitovi/convey/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/bitovi/convey

Made for: GitHub Copilot.

Per session 2,187 This file is loaded in full into every session.
When invoked 2,187 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 $0.02187 $0.02187
Opus 5 $0.01094 $0.01094
Sonnet 5 $0.00437 $0.00437
Haiku 4.5 $0.00219 $0.00219

Measured 2d ago against content hash 432c6a990ce3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

convey copilot-instructions.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 2d 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.

.github/copilot-instructions.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Convey MCP — Copilot Instructions

Project Overview

A browser overlay + inspector panel + MCP server for visually editing Tailwind CSS classes on a running React or Angular app. The user clicks elements in the page, and the panel lets them scrub/select new Tailwind values which are queued as changes for an AI agent to apply.

Stack: TypeScript, React 18, Angular 21, Vite 5, Tailwind v4 (CSS-only @theme), Express + WebSocket, MCP SDK, Vitest, Storybook 8 + 10, esbuild.

Key Design Tokens (Bitovi brand)

Used throughout panel UI — do not substitute generic colors:

bit-teal:      #00848B
bit-orange:    #F5532D
bit-surface:   panel background
bit-surface-hi: elevated surface
bit-bg:        page background
bit-border:    border color
bit-text:      primary text
bit-text-mid:  secondary text
bit-muted:     muted/disabled text

Code Conventions

  • TypeScript everywhere — no plain JS files in overlay/, panel/, or server/
  • No @/ path alias — use relative imports (../../overlay/src/class-parser)
  • No cn() utility — use template literals for conditional classes
  • No default exports for components — use named exports
  • React function components only — no class components

Running Everything

Preferred: VS Code Tasks (run individually for full visibility)

Start each process as a separate task via Terminal → Run Task so you can see each terminal independently:

  1. Watch: Overlay — esbuild --watch, rebuilds overlay/dist/overlay.js on every save
  2. Watch: Panelvite build --watch, rebuilds panel/dist/ on every save
  3. Mock MCP Client — spawns its own MCP server (port 3333) via stdio, so no separate server task is needed. Loops: implement_next_change → 2s simulated work → mark_change_implemented → repeat. Stage + commit patches in the panel and watch the mock agent pick them up.
  4. Test App (port 5173) — Vite dev server for the test app

Tip: The Mock MCP Client prints exactly what an AI agent receives from implement_next_change, making it easy to observe the full loop end-to-end.

Read the full file on GitHub · 184 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.

  1. 2d ago First seen · 184 lines · 2,187 tokens per session scan A 432c6a990ce3

Subscribe to this mod's changes

convey copilot-instructions.md is an instructions file published in the GitHub repository bitovi/convey (46 stars, last pushed 16d ago), licensed MIT. It adds 2,187 tokens to every session, about $0.0109 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.