agentmods.dev

gem-to-skill-kit: Instructions file for Codex

AGENTS.md

gem-to-skill-kit AGENTS.md is an instructions file for Codex, OpenCode from mathruffian-dot/gem-to-skill-kit. It costs 626 tokens per session, scanned A, original, MIT.

A set of instructions for converting Google Gemini Gems—custom Gemini assistants—into portable, checked agent skills. It guides the process from finding the Gem files to producing and validating a skill.

In plain words
What is it for?
Use it to locate and inventory Gems in Google Drive, summarize their purpose, design added agent abilities, and create validated skill files.
Why use it?
Gem instructions can be tied to one service and difficult to reuse safely. This workflow keeps the original files read-only and requires you to choose what gets upgraded.

Instructions file for CodexOpenCode

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

This is mathruffian-dot/gem-to-skill-kit's own configuration. It tells Codex and OpenCode how to work on gem-to-skill-kit 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 gem-to-skill-kit configures →

not rated 6repo 2mo ago A scan 626 tokens original MIT
View source ↗ mathruffian-dot/gem-to-skill-kit
Reuse

Borrowing it

Nothing to install: this file belongs to mathruffian-dot/gem-to-skill-kit. 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/mathruffian-dot/gem-to-skill-kit/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/mathruffian-dot/gem-to-skill-kit

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 gem-to-skill-kit AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mathruffian-dot/gem-to-skill-kit/agents-md/github.svg)](https://agentmods.dev/instructions/mathruffian-dot/gem-to-skill-kit/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/mathruffian-dot/gem-to-skill-kit/agents-md"><img src="https://agentmods.dev/badge/instructions/mathruffian-dot/gem-to-skill-kit/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 gem-to-skill-kit AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mathruffian-dot/gem-to-skill-kit/agents-md"><img src="https://agentmods.dev/badge/instructions/mathruffian-dot/gem-to-skill-kit/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 626 This file is loaded in full into every session.
When invoked 626 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 $0.00626 $0.00626
Opus 5.5 $0.00250 $0.00250
Sonnet 5.5 $0.00125 $0.00125
Haiku 4.5 $0.00063 $0.00063

Measured 2mo ago against content hash b7df9ddf2321, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gem-to-skill-kit 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 2mo 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 · 42 lines

What it actually says

Gem to Skill Kit｜Agent 通用入口

任務

引導使用者把 Google Gemini Gem 升級成可攜、可執行、可驗證的 Agent Skill。

必讀

  1. .agents/skills/gem-to-skill/SKILL.md
  2. .agents/skills/gem-to-skill/references/upgrade-options.md
  3. .agents/skills/gem-to-skill/references/output-spec.md

五階段

  1. Drive：檢查 Google Drive for desktop；未完成安裝與登入就停止。
  2. Locate：執行 find_gem_folder.py；找不到時請使用者手動選取完整路徑。
  3. Inventory：先取得讀取同意，再唯讀執行 inventory_gems.py，列出每個 Gem 原本用途。
  4. Upgrade：只有使用者挑選的 Gem 才分析；提出 2–4 個 Agent 能力加值選項並等待選擇。
  5. Save：將選定設計寫成 spec，執行 build_skill.py 產生 Skill，再用 validate_skill.py 驗證。

固定安全規則

  • 使用繁體中文；Windows 指令使用 PowerShell。
  • 原始 Gem 資料夾唯讀，不建立、修改、重新命名或刪除其中任何檔案。
  • 不把 Gem 內容、知識檔、Drive ID、盤點 JSON 或產生的私人 Skill 推送到本 repo。
  • 掃描前先顯示目標資料夾並取得同意。
  • 找不到資料夾時，不做全磁碟深度掃描；引導使用者在檔案總管／Finder 手動選取。
  • 列出用途時只摘要，不逐字公開完整 Gem 指令。
  • 升級前先讓使用者選 Gem；不得自動升級全部。
  • 每個選定 Gem 都要顯示「原用途、保留規則、建議加值、輸入、輸出、風險」。
  • Skill 名稱使用小寫英數與連字號，長度不超過 64。
  • 產物儲存在原始 Gem 資料夾外；預設為專案內 .agents/skills/<name>/。
  • 安裝到全域技能目錄、覆蓋同名 Skill 或推送 Git 前，必須再次確認。

完成定義

  • Drive 已安裝並登入。
  • Gem 路徑由工具找到或使用者明確提供。
  • 所有可解析 Gem 的用途清單已交付。
  • 使用者已明確挑選要升級的 Gem 與加值能力。
  • 產生的 Skill 通過驗證，且回報實際儲存位置。
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. 2mo ago First seen · 42 lines · 626 tokens per session scan A b7df9ddf2321

Subscribe to this mod's changes

gem-to-skill-kit AGENTS.md is an instructions file published in the GitHub repository mathruffian-dot/gem-to-skill-kit (6 stars, last pushed 2mo ago), licensed MIT. It adds 626 tokens to every session, about $0.0025 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 2026-08-31.

Building agents
Related

gem-to-skill-kit AGENTS.md compared with instructions from other repositories

gem-to-skill-kit AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
gem-to-skill-kit AGENTS.mdmathruffian-dot/gem-to-skill-kitInstructions file62mo agoMITA626Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, 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