chrono-mcp AGENTS.md

chrono-mcp AGENTS.md is an instructions file for Codex, OpenCode from JMoak/chrono-mcp. It costs 1,555 tokens per session, scanned A, original, MIT.

Repository instructions for Chrono MCP, an MCP server that provides tools to AI applications through standard input and output. They document its TypeScript structure, development commands, tests, benchmarks, and interactive inspector.

In plain words
What is it for?
Use them to build and lint the project, run unit and protocol tests, benchmark batch operations, inspect the MCP server interactively, or start it directly.
Why use it?
They give a coding agent the project-specific commands and architecture needed to change, test, and run the server correctly.

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/jmoak/chrono-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/JMoak/chrono-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 chrono-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jmoak/chrono-mcp/agents-md.svg)](https://agentmods.dev/instructions/jmoak/chrono-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/jmoak/chrono-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/jmoak/chrono-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,555 This file is loaded in full into every session.
When invoked 1,555 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 $0.01555 $0.01555
Opus 5 $0.00777 $0.00777
Sonnet 5 $0.00311 $0.00311
Haiku 4.5 $0.00155 $0.00155

Measured 4d ago against content hash 7dfbf26df2d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

chrono-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 4d 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 · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file provides guidance to AI coding agents working with code in this repository.

Essential Commands

Build and Development:

  • npm run build - Compile TypeScript to dist/ directory
  • npm run clean - Remove built files
  • npm install - Install dependencies
  • npm run lint - Run Biome linter
  • npm run lint:fix - Auto-fix linting issues with Biome

Testing and Debugging:

  • npm test - Vitest unit tests; npm run test:mcp - vibrissa protocol contracts (build first)
  • npm run bench - Vitest benchmarks for batch operations at the MAX_OPERATIONS cap (10k items)
  • npm run inspector - Start MCP Inspector at http://localhost:6274 for interactive testing
  • node dist/index.js - Run the MCP server directly (requires build first)

Project Architecture

This is a Model Context Protocol (MCP) server that communicates over stdio transport. Key architectural elements:

Core Structure

  • Main server: src/index.ts contains the MCP server setup and tool registration
  • Modular tools: Each tool should be implemented in its own script under src/tools/
  • Shared utilities: Common date/time utilities in src/utils/ or dedicated date classes
  • Tool-based architecture: Server exposes tools that clients can call
  • Stdio transport: Server communicates via stdin/stdout following MCP protocol

Key Patterns

  • Zod validation: All tool parameters use Zod schemas for runtime validation and JSON Schema generation
  • Error handling: Uses McpError with proper error codes for MCP compliance
  • Tool registration: Two main handlers:
    • ListToolsRequestSchema - Returns available tools with schemas
    • CallToolRequestSchema - Executes tool calls with validation

Current Implementation

  • Server initialized with name/version metadata and tool capabilities
  • Example echo tool demonstrates the pattern:
    1. Define Zod schema for parameters
    2. Register tool in ListTools handler
    3. Handle execution in CallTool handler with validation

Read the full file on GitHub · 123 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. 4d ago First seen · 123 lines · 1,555 tokens per session scan A 7dfbf26df2d5

Subscribe to this mod's changes

chrono-mcp AGENTS.md is an instructions file published in the GitHub repository JMoak/chrono-mcp (0 stars, last pushed 25d ago), licensed MIT. It adds 1,555 tokens to every session, about $0.0078 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 2026-08-31.