mcify: Instructions file for Codex

AGENTS.md

mcify AGENTS.md is an instructions file for Codex, OpenCode from Lelemon-studio/mcify. It costs 2,286 tokens per session, scanned A, original, Apache-2.0.

A project instruction file for AI coding assistants working on mcify, an open-source tool that turns APIs into MCP servers. It explains the codebase layout, conventions, and rules that must not be broken.

In plain words
What is it for?
Use it to guide AI-assisted work on mcify, including understanding its TypeScript packages, architecture, and compatibility requirements.
Why use it?
It gives coding agents the context they need to make changes that fit the repository and avoid breaking important assumptions.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions subagents; mentions Claude Code; mentions AGENTS.md.

This is Lelemon-studio/mcify's own configuration. It tells Codex and OpenCode how to work on mcify 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 mcify configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Lelemon-studio/mcify. 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/Lelemon-studio/mcify/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Lelemon-studio/mcify

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 mcify AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lelemon-studio/mcify/agents-md/github.svg)](https://agentmods.dev/instructions/lelemon-studio/mcify/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/lelemon-studio/mcify/agents-md"><img src="https://agentmods.dev/badge/instructions/lelemon-studio/mcify/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 mcify AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/lelemon-studio/mcify/agents-md"><img src="https://agentmods.dev/badge/instructions/lelemon-studio/mcify/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,286 This file is loaded in full into every session.
When invoked 2,286 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.02286 $0.02286
Opus 5.5 $0.00914 $0.00914
Sonnet 5.5 $0.00457 $0.00457
Haiku 4.5 $0.00229 $0.00229

Measured 2mo ago against content hash 87eeff75f186, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcify AGENTS.md scanned grade A with 1 finding 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- `@mcify/core` and `packages/runtime/src/dispatch.ts` MUST run on Cloudflare Workers, Bun, and Node alike. **No Node-only APIs** (`node:fs`, `node:child_process`, `process.cwd()`, etc.) in those modules.
AGENTS.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — AI agent instructions for mcify

This file is read by AI coding assistants (Claude Code, Cursor, Cody, Windsurf, Copilot Workspace, OpenAI Codex, etc.) to understand the codebase and project conventions. Keep it tight and actionable. When something here goes stale, fix it in the same PR that exposed the staleness.

TL;DR

mcify is an open-source platform that turns any API into an MCP (Model Context Protocol) server. CLI-first, local-first, dev-friendly. Apache 2.0. Maintained by Lelemon Studio.

Stack: TypeScript (strict, ESM), Hono, Zod, Pino (opt-in), esbuild, pnpm workspaces, Vitest, Turbo, ESLint flat config, Changesets.

Three publishable packages under the @mcify scope on npm:

Package Role
@mcify/cli The mcify binary: init, dev, build, generate
@mcify/core Builder lib: defineTool, defineResource, definePrompt, defineConfig, schemas, auth
@mcify/runtime MCP server runtime: stdio + HTTP transports, multi-target adapters

Repository layout

mcify/
├── packages/
│   ├── core/         @mcify/core — pure TS, no runtime deps beyond zod
│   ├── runtime/      @mcify/runtime — Hono + MCP SDK + Pino
│   ├── cli/          @mcify/cli — esbuild + tsx + chokidar
│   ├── inspector/    (Phase B — not yet present)
│   └── examples/     Reference connectors (Phase C)
├── apps/
│   └── docs/         mcify.dev (Astro Starlight, placeholder)
├── .changeset/       Changesets — release management
├── .github/
│   └── workflows/    CI (typecheck/lint/test/build) and Release (changesets/action)
├── .claude/          Slash commands and subagents for Claude Code
├── docs/decisions/   ADRs (Architecture Decision Records)
└── eslint.config.js  Flat config, applies to the whole monorepo

Critical invariants — break these and things go wrong

Workers / edge compatibility

  • @mcify/core and packages/runtime/src/dispatch.ts MUST run on Cloudflare Workers, Bun, and Node alike. No Node-only APIs (node:fs, node:child_process, process.cwd(), etc.) in those modules.
  • Pino logger is opt-in — Pino uses node:fs internals and breaks on Workers. Default is createConsoleLogger, which is portable.
  • Adapters in packages/runtime/src/adapters/{node,bun,workers}.ts are runtime-specific. Node-only code lives there, not in shared modules.
  • Cloudflare Workers do not preserve module-level state across cold starts in the way Node does. The Hono app must be built once per handler instance, not per request (we hit this bug in createWorkersHandler).

Read the full file on GitHub · 158 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 · 158 lines · 2,286 tokens per session scan A 87eeff75f186

Subscribe to this mod's changes

mcify AGENTS.md is an instructions file published in the GitHub repository Lelemon-studio/mcify (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 2,286 tokens to every session, about $0.0091 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

mcify AGENTS.md compared with instructions from other repositories

mcify AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcify AGENTS.mdLelemon-studio/mcifyInstructions file24mo agoApache-2.0A2,286Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode