supercli AGENTS.md

Project instructions for Supercode, a monorepo—a repository containing multiple apps and packages—using Bun as its package manager.

In plain words
What is it for?
Use them when changing the Supercode codebase, running all or individual app and package commands, or working with its database migrations and tests.
Why use it?
They give coding agents the correct commands and project rules for building, testing, linting, and checking types across the repository.

Instructions file for CodexOpenCode

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/yashdev9274/supercli/agents-md
Clone the repo
git clone --depth 1 https://github.com/yashdev9274/supercli

Made for: Codex, OpenCode.

Per session 1,750 This file is loaded in full into every session.
When invoked 1,750 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 $0.01750 $0.01750
Opus 5 $0.00875 $0.00875
Sonnet 5 $0.00350 $0.00350
Haiku 4.5 $0.00175 $0.00175

Measured yesterday against content hash b50e2a7201e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

supercli 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 yesterday.

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 · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions for Supercode Monorepo

Build Commands

# Root level commands
bun run dev          # Start all dev servers
bun run build        # Build all packages and apps
bun run lint         # Run linting across all packages
bun run typecheck    # Run TypeScript checks across all packages

# Individual app/package commands
bun run dev:web      # Start only web app (Next.js)
bun run dev:api      # Start only API app
bun run dev:cli      # Start only CLI app

# Package-specific commands (run from package directory)
cd packages/db && bun run db:generate    # Generate Prisma client
cd packages/db && bun run db:migrate     # Deploy Prisma migrations

Note: This project uses Bun as the package manager ([email protected]).

Testing

Uses bun test (Bun's built-in test runner). Test files use *.test.ts convention.

# Run all tests
bun test

# Run a single test file
bun test path/to/file.test.ts

# Run tests in watch mode
bun test --watch

Code Style Guidelines

Imports

  • Use absolute imports with path aliases: @/components/ui/button for web app
  • Use workspace imports for cross-package dependencies: @super/db, @super/auth
  • Import order: React/Next → External libs → Internal aliases → Relative imports
  • Group imports by category with blank lines between groups

Formatting

  • No semicolons at end of statements
  • Use double quotes for strings
  • 2-space indentation
  • Trailing commas in multi-line objects/arrays
  • No explicit return type on function components (inferred)

Naming Conventions

  • Components: PascalCase (e.g., Button.tsx, HeroSection.tsx)
  • Files: kebab-case for non-component files (e.g., utils.ts, query-provider.tsx)
  • Functions: camelCase (e.g., signIn, getSession)
  • Types/Interfaces: PascalCase (e.g., VariantProps)
  • Constants: UPPER_SNAKE_CASE for true constants

Types & TypeScript

  • Strict mode enabled (strict: true in tsconfig)
  • Use type for type aliases when possible
  • Export types explicitly when needed for consumers
  • Use interface for object shapes that may be extended
  • Prefer explicit return types on library functions

Read the full file on GitHub · 146 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. yesterday First seen · 146 lines · 1,750 tokens per session scan A b50e2a7201e9

Subscribe to this mod's changes

supercli AGENTS.md is an instructions file published in the GitHub repository yashdev9274/supercli (207 stars, last pushed yesterday), licensed MIT. It adds 1,750 tokens to every session, about $0.0088 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.