machine-bridge-mcp: Instructions file for Codex

AGENTS.md

machine-bridge-mcp AGENTS.md is an instructions file for Codex, OpenCode from YuLeiFuYun/machine-bridge-mcp. It costs 5,860 tokens per session, scanned A, original, MIT.

A set of repository instructions for automating work in the YuLeiFuYun/machine-bridge-mcp project, including rules for choosing tools and handling GitHub tasks.

In plain words
What is it for?
Use it when working in that repository to check required documents, choose approved tools, limit the work's scope, and use local Git or GitHub commands.
Why use it?
It keeps work within the repository's required boundaries, especially by preventing hosted GitHub tools from being used when local tools are required.

Instructions file for CodexOpenCode

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

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

Reuse

Borrowing it

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

README.md
[![agentmods](https://agentmods.dev/badge/instructions/yuleifuyun/machine-bridge-mcp/agents-md.svg)](https://agentmods.dev/instructions/yuleifuyun/machine-bridge-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/yuleifuyun/machine-bridge-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/yuleifuyun/machine-bridge-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 5,860 This file is loaded in full into every session.
When invoked 5,860 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 $0.05860 $0.05860
Opus 5 $0.02930 $0.02930
Sonnet 5 $0.01172 $0.01172
Haiku 4.5 $0.00586 $0.00586

Measured yesterday against content hash 1b54bfb609b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

machine-bridge-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 yesterday.

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 · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository automation contract

Tool-selection hard gate

For this repository, every hosted GitHub control plane is out of scope even when the ChatGPT host, tool registry, or connector catalog exposes one. Before any GitHub-related tool discovery, schema loading, read, or mutation, use Machine Bridge to load this repository contract and keep all GitHub activity on the owner's machine.

  • Do not call, discover, list, load, or invoke a hosted GitHub connector, ChatGPT GitHub plugin, browser-side GitHub integration, or equivalent remote tool.
  • Use only local git, gh, and gh api executed through Machine Bridge.
  • This gate applies before connector/tool discovery, not only before the eventual GitHub mutation.
  • If Machine Bridge or the local authenticated GitHub CLI is unavailable, stop and report the boundary. Availability of a hosted connector is not a fallback.

A violation must be treated as a process defect: verify whether any remote effect occurred using local gh, record the correction in the current task, and continue only through the local control plane.

Read docs/ENGINEERING.md, docs/PROJECT_STANDARDS.md, and CONTRIBUTING.md before changing this repository.

Before describing a checkout as current main, the online version, or a release candidate, verify identity instead of trusting the directory name. Inspect git worktree list --porcelain, the current branch/HEAD, package.json version, and src/shared/server-metadata.json tool-schema generation. When the owner names a specific prerelease such as beta.N, resolve the matching worktree before treating any checkout as the task target by running python3 "$HOME/.codex/scripts/resolve-versioned-worktree.py" <any-worktree-of-this-repository> <beta.N>. Accept only one status=resolved result with fallback_used=false. An available branch/worktree identity for the requested prerelease is stronger routing evidence than a mutable working-tree version; a dirty package.json version that diverges from HEAD must never be sufficient by itself to select a checkout. The canonical directory name machine-bridge-mcp, shortest path, current shell directory, and historical dirty worktrees are never freshness evidence or fallback targets. If the resolver reports missing, ambiguous, unavailable, or dirty-version-only evidence, stop the routing decision and reconcile the worktree inventory instead of silently choosing another checkout. If comparing with a deployed runtime, also verify live server_info.version and tool_delivery.tool_schema_generation; if hosted schema behavior matters, load the complete unfiltered machine-mcp tool catalog as the separate host-owned snapshot. A mismatch blocks the readiness claim. Never delete or repurpose a dirty historical worktree merely to make the directory layout look canonical; preserve or archive its uncommitted state first.

Read the full file on GitHub · 161 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. yesterday Changed · +409 tokens per session 1b54bfb609b0
  2. 4d ago Changed · +1 lines · +236 tokens per session de000bc9d4b5
  3. 8d ago First seen · 160 lines · 5,215 tokens per session scan A 84c04555a931

Subscribe to this mod's changes

machine-bridge-mcp AGENTS.md is an instructions file published in the GitHub repository YuLeiFuYun/machine-bridge-mcp (1 stars, last pushed today), licensed MIT. It adds 5,860 tokens to every session, about $0.0293 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens