agentmods.dev

fileterm: Instructions file for Codex

AGENTS.md

fileterm AGENTS.md is an instructions file for Codex, OpenCode from St0ff3l/fileterm. It costs 2,115 tokens per session, scanned A, original, MIT.

An entry guide to the FileTerm codebase for coding agents. It explains the project's purpose, where its architecture and design documents live, and boundaries between Rust, Tauri, the user interface, shared types, and network protocols.

In plain words
What is it for?
Use it when starting work in FileTerm, especially for tasks crossing Rust commands, the Tauri bridge, React screens, shared packages, SSH/SFTP/FTP services, or project documentation.
Why use it?
It helps an agent find the relevant project rules and avoid changing the wrong layer or relying on outdated Electron code.

Instructions file for CodexOpenCode

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

This is St0ff3l/fileterm's own configuration. It tells Codex and OpenCode how to work on fileterm 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 fileterm configures →

not rated 422repo +1 changed 10d ago A scan 2,115 tokens original MIT
View source ↗ St0ff3l/fileterm
Reuse

Borrowing it

Nothing to install: this file belongs to St0ff3l/fileterm. 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/St0ff3l/fileterm/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/St0ff3l/fileterm

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 fileterm AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/st0ff3l/fileterm/agents-md/github.svg)](https://agentmods.dev/instructions/st0ff3l/fileterm/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/st0ff3l/fileterm/agents-md"><img src="https://agentmods.dev/badge/instructions/st0ff3l/fileterm/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 fileterm AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/st0ff3l/fileterm/agents-md"><img src="https://agentmods.dev/badge/instructions/st0ff3l/fileterm/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,115 This file is loaded in full into every session.
When invoked 2,115 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 $0.02115 $0.02115
Opus 5.5 $0.00846 $0.00846
Sonnet 5.5 $0.00423 $0.00423
Haiku 4.5 $0.00212 $0.00212

Measured 10d ago against content hash a05a16d0b648, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fileterm 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 10d 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 · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FileTerm Agent Guide

FileTerm 是 Rust + Tauri + React + TypeScript 桌面远程工作台。仅维护 apps/tauri 运行时；不得重新引入已移除的 Electron 目录、依赖、脚本或 CI 配置。

工作范围与 Git

  • 默认直接在用户打开或指定的项目目录工作；仅在用户明确要求时使用 worktree。切换分支前检查并保留未提交修改，不覆盖用户工作。
  • 新分支按任务选择 feat/、fix/、chore/、docs/、release/<version>；小写 kebab-case，不默认使用 codex/。
  • PR 默认使用普通 Merge（Create a merge commit）；用户明确指定时才使用其他策略。
  • 修复、创建 PR 或合并 PR 不表示 Issue 已解决。使用 Refs #123 / Related to #123，禁止自动关闭关键词；仅在用户明确确认发布并验证通过且允许关闭后关闭 Issue。
  • 在已授权范围内完成实现、验证和必要修复；只在缺少关键输入或需要超出授权范围时询问。完成报告说明改动、验证结果与未验证项。
  • 桌面 UI 验证按当前项目的 npm run dev 进程识别。macOS 开发运行的是小写 fileterm（apps/tauri/src-tauri/target/debug/fileterm）；先核对进程路径、工作目录、Vite 端口和页面版本。不要用可能自动启动应用的名称/包 ID 查询探测窗口：FileTerm Dev / com.fileterm.desktop.dev 可能启动旧 .app，小写 fileterm 也可能被忽略大小写后匹配到 /Applications/FileTerm.app。工具无法精确绑定当前未打包进程时，停止桌面操作并报告，不启动其他版本代替验证；详见 开发版识别与预览。

按任务读取

只读取当前任务需要的资料；小修正不要求先读全部文档。

任务 入口
跨 Rust / bridge / renderer / packages 层，或改变服务边界 架构 与相关 进行中计划
React/TSX、组件 CSS、主题、控件或独立窗口 UI 通用组件 skill；视觉设计另见 设计规范
平台差异、原生窗口/菜单、快捷键、终端手势/字体 跨平台 skill
FileTerm 应用图标、Dock、任务栏、Linux 启动器、tray 与尺寸问题 应用图标 skill；平台约束
SSH 平台探测、CWD、sudo/root、凭据与旧 Comware 平台与协议约束
运行或截图验证桌面 UI 开发版识别与预览
UI/UX 方案、配色/布局探索或体验审查 设计检索 skill
版本说明、tag、Release 与发布流水线 发布 skill
阶段目标 / 隐藏入口 / 架构决策 路线图、隐藏功能、决策

Read the full file on GitHub · 76 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. 10d ago Changed a05a16d0b648
  2. 14d ago Changed · +1 lines · +58 tokens per session 1b5679f0a71a
  3. 19d ago Changed · +1 lines · +179 tokens per session 28208d42f244
  4. 28d ago Changed · -144 lines · -3,155 tokens per session 3794118a554d
  5. 1mo ago Changed · +17 tokens per session 615b6c70a5e8
  6. 1mo ago Changed · +7 lines · +270 tokens per session a24fbd32c58a
  7. 1mo ago Changed · +1 lines · +126 tokens per session f3557ce4cecd
  8. 1mo ago Changed · +3 lines · +243 tokens per session 558ac9fa15ca
  9. 2mo ago Changed · +22 lines · +974 tokens per session 7b85f8bd9e7a
  10. 2mo ago First seen · 185 lines · 3,403 tokens per session scan A 2677c366e71d

Subscribe to this mod's changes

fileterm AGENTS.md is an instructions file published in the GitHub repository St0ff3l/fileterm (422 stars, last pushed 2d ago), licensed MIT. It adds 2,115 tokens to every session, about $0.0085 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 2026-08-30.

FTPReactdesktop-applicationdevops-toolsftp-clientmonaco-editor
Related

fileterm AGENTS.md compared with instructions from other repositories

fileterm AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
fileterm AGENTS.mdSt0ff3l/filetermInstructions file4222d agoMITA2,115Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode