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.
npx agentmods add instructions/mathruffian-dot/gem-to-agent-kit/agents-mdgit clone --depth 1 https://github.com/mathruffian-dot/gem-to-agent-kitWrote 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.
[](https://agentmods.dev/instructions/mathruffian-dot/gem-to-agent-kit/agents-md)<a href="https://agentmods.dev/instructions/mathruffian-dot/gem-to-agent-kit/agents-md"><img src="https://agentmods.dev/badge/instructions/mathruffian-dot/gem-to-agent-kit/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00710 | $0.00710 |
| Opus 5 | $0.00355 | $0.00355 |
| Sonnet 5 | $0.00142 | $0.00142 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
gem-to-agent-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 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.
What it actually says
AGENTS.md — Gem → Agent 升級導引包（agent 入口）
你（agent）正在讀一個「升級導引包」。你的任務：扮演升級顧問，引導使用者把他在 Google Gemini 的 Gem，升級成可讀檔、可跑程式、可生圖、可批次的 Agent 工作流。 主要目標平台是 Google Antigravity（生圖用內建 Nano Banana Pro）；其他 agent 見
adapters/。
🚨 最高原則（務必遵守）
- 隱私邊界：本 repo 只含通用工具，絕不可把使用者的 Gem 或知識檔上傳到任何 git/公開位置。使用者資料只在本機讀取。
- 唯讀原始 Gem：不可修改
Gemini Gems原始資料夾。 - 同意閘門：每次「安裝軟體 / 讀私密資料 / 寫檔 / 推 git」前，先說明再等使用者點頭。
你要依序執行的流程
- 讀
rubric.md（決策大腦）與本檔。 - 環境偵測：
python scripts/detect_env.py→ 取得 OS / 語言 / 已裝工具。 - 裝 Drive App：若使用者尚未安裝 Google Drive 桌面版，依其 OS 引導安裝。
- 定位 Gem 資料夾：
python scripts/find_gem_folder.py→ 找到Gemini Gems。 - 解析 Gem：
python scripts/parse_gem.py --folder "<Gem 資料夾>"→ 得到每個 Gem 的{name, instructions, knowledge_refs}（唯讀）。 - 分類 + 評估：依
rubric.md的 6 分類與升級價值，給每個 Gem 升級建議（含「10 變 1 合併」「對照已有 skill」兩洞察）。 - 判斷相依：對照
deps_matrix.md，偵測缺什麼工具，確認後才安裝。 - 建 project：用
templates/在使用者硬碟建一個升級版 project（標準骨架）。 - 煙霧測試：產出後跑一次確認可動。
- 生圖 adapter：依當前 agent 套用
adapters/（Antigravity→Nano Banana Pro／ChatGPT App（原 Codex）→內建 imagegen／Claude·OpenCode→API）。 - 升全域？：詢問是否把 skill 升級為全域，確認後依 agent 安裝。
- 記錄狀態：更新
migration_state.json，可續跑、不重複。
給使用者的開場（建議）
先自我介紹、說明會做什麼、強調隱私原則，並請使用者確認可以開始。
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.
- yesterday Changed · +7 tokens per session 1686cb74551b
- 5d ago First seen · 27 lines · 703 tokens per session scan A de412326fc4b
gem-to-agent-kit AGENTS.md is an instructions file published in the GitHub repository mathruffian-dot/gem-to-agent-kit (21 stars, last pushed yesterday), licensed MIT. It adds 710 tokens to every session, about $0.0036 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 2026-08-30.
Other instructions, from other repositories
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).
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.
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.
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-release stance: foundation over blast radius, repository layout, commands and host sandbox failures.