rclone-mcp-server: Instructions file for Codex

AGENTS.md

rclone-mcp-server AGENTS.md is an instructions file for Codex, OpenCode from angenge/rclone-mcp-server. It costs 926 tokens per session, scanned A, original, MIT.

A project instruction document for deploying and checking an rclone MCP server. rclone is a tool for connecting to and managing files on remote storage, while an MCP server exposes tools for another program to call.

In plain words
What is it for?
It is for guiding Docker Compose deployment, checking the remote rclone service, viewing logs, and following repository commit conventions.
Why use it?
It keeps deployment details, access checks, storage paths, container settings, and known project rules in one place.

Instructions file for CodexOpenCode

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

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

Reuse

Borrowing it

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

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 rclone-mcp-server AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/angenge/rclone-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/angenge/rclone-mcp-server/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 926 This file is loaded in full into every session.
When invoked 926 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 $0.00926 $0.00926
Opus 5.5 $0.00370 $0.00370
Sonnet 5.5 $0.00185 $0.00185
Haiku 4.5 $0.00093 $0.00093

Measured 2d ago against content hash dd98517c5995, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rclone-mcp-server 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl.exe -sk -u "$RC_USER:$RC_PASS" -X POST "https://<RCD_DOMAIN>/core/version" -H "Content-Type: application/json" -d "{}"
AGENTS.md · 38 lines

How it starts

The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

部署信息

项目 说明
组件/角色 远端 rclone rcd(RC API)+ 本仓库 rclone-mcp-server(MCP 代理)
服务器 vps = deploy@<RCD_HOST_IP>:10022(rcd 所在);onecloud = deploy@<AUX_HOST_IP>:22
部署路径 /home/<DEPLOY_USER>/APPs/rclone(docker compose 项目 rclone,compose 文件位于该目录)
部署方式 docker compose up -d(容器 rclone-rcd,镜像 rclone/rclone:1.69.3,restart=always,healthcheck healthy)
容器名 rclone-rcd
日志路径 docker logs -f rclone-rcd
数据/配置 配置文件 /home/<DEPLOY_USER>/APPs/rclone/config/rclone.conf(挂载为 /config/rclone.conf);缓存 /home/<DEPLOY_USER>/APPs/rclone/cache;数据盘挂载 /DATA/gdrive-acct-a(gd-acct-a:)、/DATA/gdrive-acct-b(gd-acct-b:),均 fuse.rclone、allow_other;RC 访问凭据只存于反向代理配置,不落盘
部署时间 2026-08-04 09:06 UTC(容器启动时间)
运行参数 rcd --config=/config/rclone.conf --rc-web-gui --rc-addr=0.0.0.0:5572 --log-level=INFO --retries=10 --retries-sleep=60s --timeout=10m --buffer-size=64M --use-mmap --tpslimit=10 --tpslimit-burst=10 --user-agent=Mozilla/5.0 ...

公开入口:https://<RCD_DOMAIN>(反向代理至容器 5572,Basic Auth <RC_USER>,密码存于代理配置)。

rcd 访问验证

curl.exe -sk -u "$RC_USER:$RC_PASS" -X POST "https://<RCD_DOMAIN>/core/version" -H "Content-Type: application/json" -d "{}"

已知问题

  • 默认工具集不含 local:,对远端 rcd 调用 operations/stat fs=local: 会报 500 didn't find section in config file ("local"),须使用 rcd 已配置的远端名(如 gd-acct-b:)。

Git 提交约定

  • 未经用户明确要求,不主动 commit / push / 创建 PR。
  • 提交作者信息: 使用 git 登录(全局配置)的作者信息(user.name)和邮箱(user.email);如本地配置不符,主动询问用户如何选择。
  • 提交前先检查 git status、git diff 与 git log --oneline -10,只暂存本次改动相关文件,绝不提交凭据/密钥(.env、*.pem 等)。
  • 提交信息使用英文,格式:<type>: <concise description>(type 可选 feat / fix / docs / refactor / chore / style / test 等等),如 docs: Update the deployment documentation;简单改动可只用简洁描述,不必强行加前缀。
  • 提交信息概括「做了什么 + 为什么」,不堆砌无关细节;一次提交对应一个逻辑改动,避免把不相关修改混在一起。
  • 若一次改动同时包含多种类型(如既有 feat 也有 fix),能拆则拆成多个提交分别提交(分别 git add 相关文件);若改动交织在同一处无法拆分,则以影响最大的类型为前缀并在信息中说明。
  • 提交失败或 hook 拒绝时,修复后新建提交,不 amend、不 force push。

Read the full file on GitHub · 38 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. 2d ago First seen · 38 lines · 926 tokens per session scan A dd98517c5995

Subscribe to this mod's changes

rclone-mcp-server AGENTS.md is an instructions file published in the GitHub repository angenge/rclone-mcp-server (0 stars, last pushed 3d ago), licensed MIT. It adds 926 tokens to every session, about $0.0037 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-16.

Related

rclone-mcp-server AGENTS.md compared with instructions from other repositories

rclone-mcp-server AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
rclone-mcp-server AGENTS.mdangenge/rclone-mcp-serverInstructions file03d agoMITA926Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file283ktodayMITA4,342Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot