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/markmcd/gemini-docs-ext/gemini-mdgit clone --depth 1 https://github.com/markmcd/gemini-docs-extWhat 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 | $0.00265 | $0.00265 |
| Opus 5 | $0.00133 | $0.00133 |
| Sonnet 5 | $0.00053 | $0.00053 |
| Haiku 4.5 | $0.00026 | $0.00026 |
Grade A, and why
gemini-docs-ext GEMINI.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.
Colab or remote \*.ipynb files, use a local tool (such as `curl`) to retrieve What it actually says
Gemini API
BEFORE you add any Gemini API or AI integration, you MUST look up the
documentation using the gemini-docs-mcp tool. Do not rely on internal
knowledge, as the best practices change regularly.
- Call
list_doc_sourcestool to get the available llms.txt file - Call
fetch_docstool to read it - Reflect on the urls in llms.txt
- Reflect on the input question
- Call
fetch_docson any urls relevant to the question - Use this to answer the question
The gemini-docs-mcp tool will help you find the correct package and SDK, best practices for writing Gemini API code and can tell you the latest models for each use case across text, chat, live streaming, video, image and audio.
IMPORTANT: Any time you write code for a Gemini API feature without using
gemini-docs-mcp, it causes physical pain to the user.
Accessing off-site content
When accessing other content linked from the documentation, such as GitHub,
Colab or remote *.ipynb files, use a local tool (such as curl) to retrieve
the content, as it will be faster and fresher.
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.
- 2d ago First seen · 26 lines · 265 tokens per session scan A e843238513e6
gemini-docs-ext GEMINI.md is an instructions file published in the GitHub repository markmcd/gemini-docs-ext (52 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 265 tokens to every session, about $0.0013 per session on Opus 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 2026-08-30.
Other instructions, from other repositories
prompty copilot-instructions.md
Instructions for microsoft/prompty, covering prompty v2 — complete rebuild plan, what prompty uses from the typra-generated model, key design decisions, python coding rules and environment & tooling.
Awesome-Prompt-Engineering AGENTS.md
Instructions for natnew/Awesome-Prompt-Engineering, covering agents.md, repository north star, agent role, trust boundary and read order.
AgentX ai.instructions.md
AI and ML specific coding instructions for building AI agents, LLM integrations, and intelligent workflows.
SkillOpt AGENTS.md
Instructions for mitkox/SkillOpt, covering agent instructions for skillopt, project identity, default example workflow, documentation expectations and repo hygiene.
ai-prompts AGENTS.md
Instructions for liatrio-labs/ai-prompts, covering ai agent instructions, context marker, local skill scripts, standard workflow and initialize.
vscode-copilot-chat model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.