agentmods.dev

ultra-mcp: Instructions file for Codex

AGENTS.md

ultra-mcp AGENTS.md is an instructions file for Codex, OpenCode from RealMikeChong/ultra-mcp. It costs 663 tokens per session, scanned A, original, MIT.

Repository instructions for the ultra-mcp project, a TypeScript command-line and MCP server project with a dashboard and database files.

In plain words
What is it for?
Use them to build the CLI or dashboard, run unit, integration, UI, or end-to-end tests, and organize changes in the project.
Why use it?
They explain the project layout, build commands, test commands, and coding conventions before you make changes.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is RealMikeChong/ultra-mcp's own configuration. It tells Codex and OpenCode how to work on ultra-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ultra-mcp configures →

not rated 277repo 1y ago A scan 663 tokens original MIT
View source ↗ RealMikeChong/ultra-mcp
Reuse

Borrowing it

Nothing to install: this file belongs to RealMikeChong/ultra-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/RealMikeChong/ultra-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/RealMikeChong/ultra-mcp

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for ultra-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/realmikechong/ultra-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/realmikechong/ultra-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/realmikechong/ultra-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/realmikechong/ultra-mcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ultra-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/realmikechong/ultra-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/realmikechong/ultra-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 663 This file is loaded in full into every session.
When invoked 663 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00663 $0.00663
Opus 5.5 $0.00265 $0.00265
Sonnet 5.5 $0.00133 $0.00133
Haiku 4.5 $0.00066 $0.00066

Measured 2mo ago against content hash 75d0edddc0aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ultra-mcp 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 2mo 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.

AGENTS.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Structure & Module Organization

  • src/: TypeScript sources for the CLI and MCP server.
    • Key modules: src/cli.ts, src/server.ts, src/commands/, src/providers/, src/config/, src/db/, src/api/, src/utils/, src/vector/.
  • src/__tests__/: Unit, integration, and e2e tests; shared setup.ts.
  • drizzle/: SQL schema/migrations and artifacts.
  • web/: Dashboard app (built separately); output in dist-web/.
  • Build outputs: dist/ (CLI), dist-web/ (dashboard).

Build, Test, and Development Commands

  • Install deps: bun install (preferred) or npm install.
  • Build CLI: bun run build → emits dist/cli.js (executable) and copies drizzle/.
  • Build dashboard: bun run build:dashboard (runs inside web/).
  • Build all: bun run build:all (CLI + dashboard).
  • Dev watch (CLI): bun run dev.
  • Run dashboard in dev via CLI: bun run dev:api (builds then serves dashboard with --dev).
  • Tests: bun run test (default), bun run test:all, coverage bun run test:coverage, UI bun run test:ui, e2e bun run test:e2e.

Coding Style & Naming Conventions

  • Language: TypeScript (ES2022 modules). Indentation: 2 spaces.
  • Filenames: kebab-case for files/dirs (e.g., start-server.ts); tests end with .test.ts.
  • Linting: ESLint + @typescript-eslint. Run bun run lint or bun run lint:fix.
  • Console usage: no-console enforced except in CLI, config, utils, API, tests, and mocks (see eslint.config.js).

Testing Guidelines

  • Framework: Vitest (Node environment). Setup file: src/__tests__/setup.ts.
  • Locations: colocated *.test.ts and suites under src/__tests__/.
  • Coverage: V8 provider; reporters text/json/html. Default excludes e2e and web; use test:all to include everything.

Commit & Pull Request Guidelines

  • Commit style: Conventional Commits (feat:, fix:, chore:, refactor:) as used in history.
  • PR requirements: clear summary, rationale, linked issues, screenshots/GIFs for web/ changes, and test notes.
  • Quality gates: green tests, no lint errors, update docs/tests for behavior changes.

Read the full file on GitHub · 41 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. 2mo ago First seen · 41 lines · 663 tokens per session scan A 75d0edddc0aa

Subscribe to this mod's changes

ultra-mcp AGENTS.md is an instructions file published in the GitHub repository RealMikeChong/ultra-mcp (277 stars, last pushed 1y ago), licensed MIT. It adds 663 tokens to every session, about $0.0027 per session on Opus 5.5. 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.

Related

ultra-mcp AGENTS.md compared with instructions from other repositories

ultra-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ultra-mcp AGENTS.mdRealMikeChong/ultra-mcpInstructions file2771y agoMITA663Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file275k2d agoMITA4,313Codex, OpenCode