mcp: Instructions file for Codex

AGENTS.md

mcp AGENTS.md is an instructions file for Codex, OpenCode from Sequenzy/mcp. It costs 532 tokens per session, scanned A, original, MIT.

Project instructions for developing and maintaining Sequenzy's MCP server, the interface that lets agents use Sequenzy tools.

In plain words
What is it for?
Use them when working on the Sequenzy MCP server or changing its agent instructions and tool schema.
Why use it?
They provide the rules for keeping documentation, source code, synchronization, and tool definitions consistent.

Instructions file for CodexOpenCode

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

This is Sequenzy/mcp's own configuration. It tells Codex and OpenCode how to work on 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 mcp configures →

Reuse

Borrowing it

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

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/sequenzy/mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sequenzy/mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 532 This file is loaded in full into every session.
When invoked 532 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 $0.00532 $0.00532
Opus 5.5 $0.00213 $0.00213
Sonnet 5.5 $0.00106 $0.00106
Haiku 4.5 $0.00053 $0.00053

Measured 1mo ago against content hash 3cb688f8f55b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 1mo 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 · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sequenzy MCP - AI Agent Instructions

Source of Truth

This repository is the standalone public package for @sequenzy/mcp.

The implementation is mirrored from the main Sequenzy monorepo package:

  • Monorepo path: packages/mcp
  • Public repo: https://github.com/Sequenzy/mcp
  • Package name: @sequenzy/mcp

When both repositories are available locally, treat the monorepo packages/mcp package as the source of truth for implementation files and sync this standalone repository from it.

Sync Rules

When MCP implementation changes in the monorepo, update this standalone repo in the same change set:

  • src/**
  • package.json
  • server.json
  • tsconfig.json
  • tests under src/**/*.test.ts
  • README.md when tools, resources, setup, environment variables, or user-facing behavior changes

Keep standalone repository metadata pointed at https://github.com/Sequenzy/mcp, even when syncing files from the monorepo. In practice, package.json.repository, package.json.bugs, and server.json.repository should reference this standalone repo.

MCP Tool Schema Compatibility

MCP clients are not equally permissive. Keep published tool schemas conservative:

  • Tool inputSchema roots must stay plain type: "object" schemas with properties and optional required.
  • Do not publish anyOf anywhere in a tool inputSchema.
  • Do not put oneOf, allOf, enum, or not at the root of a tool inputSchema.
  • If a tool needs "provide either A or B", mutual exclusion, or conditional requirements, describe the rule in property descriptions and validate it inside the handler.
  • Add or update tests that assert unsupported schema keywords are not published.

Development

Use Bun for local work:

bun install
bun test
bun run type-check
bun run build

Do not require a real Sequenzy API key for unit tests. Tests must mock API calls and must not hit production systems.

Documentation

When adding or changing tools or resources:

  • Update the tool/resource list in README.md.
  • Update setup instructions if environment variables or package entry points change.
  • Include practical usage notes for non-obvious behavior, such as html vs blocks, nested segment filters, event merge tags, or dry-run flows.

Read the full file on GitHub · 60 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. 1mo ago First seen · 60 lines · 532 tokens per session scan A 3cb688f8f55b

Subscribe to this mod's changes

mcp AGENTS.md is an instructions file published in the GitHub repository Sequenzy/mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 532 tokens to every session, about $0.0021 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 2026-08-31.

Related

Other instructions, from other repositories