agent-mcp-hub AGENTS.md

agent-mcp-hub AGENTS.md is an instructions file for Codex, OpenCode from blackaxgit/agent-mcp-hub. It costs 6,484 tokens per session, scanned D, original, MPL-2.0.

A set of AGENTS.md project instructions for the agent-mcp-hub repository, including its layout, configuration, commands, technology choices, and testing guidance. AGENTS.md is a context file that many coding tools read to understand a repository.

In plain words
What is it for?
Use it when working on agent-mcp-hub code, its command sources, CI files, release process, configuration, or tests.
Why use it?
It gives coding agents the project-specific rules and background they need before changing files. This reduces mistakes caused by using the wrong commands, structure, or assumptions.

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/blackaxgit/agent-mcp-hub/agents-md
Clone the repo
git clone --depth 1 https://github.com/blackaxgit/agent-mcp-hub

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 agent-mcp-hub AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/blackaxgit/agent-mcp-hub/agents-md.svg)](https://agentmods.dev/instructions/blackaxgit/agent-mcp-hub/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/blackaxgit/agent-mcp-hub/agents-md"><img src="https://agentmods.dev/badge/instructions/blackaxgit/agent-mcp-hub/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 6,484 This file is loaded in full into every session.
When invoked 6,484 The same file — it is already loaded in full.
Security scan D 2 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 $0.06484 $0.06484
Opus 5 $0.03242 $0.03242
Sonnet 5 $0.01297 $0.01297
Haiku 4.5 $0.00648 $0.00648

Measured 4d ago against content hash 34fccd5a3772, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

agent-mcp-hub AGENTS.md scanned grade D with 2 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- **`agy` does not stream and leaves state behind.** Its entire answer is flushed at once on completion (measured), so the idle timer is its only hang protection — see the timeouts section of `README.md`. Each `--new-pro

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- **`prebuild: rm -rf dist` is load-bearing — do not remove it.** `tsc` does not clean `dist/`, so files whose sources were deleted linger and get **published**. v0.5.0 shipped dead `dist/http.js` + `dist/httpServer.js`
AGENTS.md · 229 lines

How it starts

The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

AI coding assistant context for this repository. AGENTS.md is a tool-agnostic context file read natively by many AI coding tools (Codex, Cursor, Copilot, Gemini CLI, Windsurf, …). Claude Code does not read it natively — Claude users should add @AGENTS.md to a CLAUDE.md.

Command sources: package.json scripts are authoritative — CI runs the same ones. No Makefile/Taskfile. Local overlay (read the nearer file when work touches those paths):

Path Read when
.github/workflows/AGENTS.md Touching CI, the release pipeline, or anything that publishes. Those rules are load-bearing and break publishing silently if got wrong.

Overview

  • Purpose: One MCP server that bridges multiple CLI coding agents — Codex, Cursor, OpenCode, Claude, and Antigravity (agy) — into any MCP client.
  • Owner: TODO: team / maintainer
  • Type: app — a published npm package (agent-mcp-hub, public on npm)
  • Stack: Node ESM ("type": "module"), TypeScript, engines.node >= 22, npm (package-lock.json)
  • Runtime deps: @modelcontextprotocol/sdk, zod. Everything else is dev-only.
  • Transport: stdio only. The HTTP transport and Docker packaging were removed in v0.5.0 — a container cannot see the caller's repo path or reuse their CLI logins, which broke the product contract.
  • Distribution: npm + the MCP Registry (server.json). Released automatically — see PUBLISHING.md.

Commands

npm ci                 # install from package-lock
npm run dev            # run from source via tsx (no build step)
npm run build          # prebuild wipes dist/, then tsc -> dist/
npm test               # vitest run
npm run test:coverage  # vitest + coverage (97% thresholds enforced)
npm run typecheck      # tsc -p tsconfig.test.json  (covers src + tests)
npm run lint           # eslint .
npm run format         # prettier --write .   (format:check to verify only)

Read the full file on GitHub · 229 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 · 229 lines · 6,484 tokens per session scan D 34fccd5a3772

Subscribe to this mod's changes

agent-mcp-hub AGENTS.md is an instructions file published in the GitHub repository blackaxgit/agent-mcp-hub (0 stars, last pushed yesterday), licensed MPL-2.0. It adds 6,484 tokens to every session, about $0.0324 per session on Opus 5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.