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 rules/nedcodes-ok/cursorrules-collection/gemini-mdgit clone --depth 1 https://github.com/nedcodes-ok/cursorrules-collectionWhat 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 | $0.00000 | $0.00570 |
| Opus 5 | $0.00000 | $0.00285 |
| Sonnet 5 | $0.00000 | $0.00114 |
| Haiku 4.5 | $0.00000 | $0.00057 |
Grade A, and why
gemini-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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GEMINI.md Rules
GEMINI.md provides instructional context to the Gemini CLI. It's loaded with every prompt, so instructions defined once apply to every interaction without repeating them.
Discovery Hierarchy
- Global:
~/.gemini/GEMINI.md— default instructions for all projects - Project root and ancestors: Gemini CLI searches for GEMINI.md from your current working directory up through each parent directory to the project root (identified by
.gitfolder) - Sub-directory files: Also scans subdirectories below your current working directory. Respects
.gitignoreand.geminiignore - All found files are concatenated and sent with every prompt. The CLI footer shows the number of loaded context files
What Goes In GEMINI.md
- Coding style: indentation, naming conventions, formatting preferences
- Project-specific patterns: "prefix interface names with
I," "use strict equality," "always add JSDoc comments" - Tool preferences: build system, test framework, package manager
- Architecture context: what the project does, how it's structured, key directories
The /memory Command
- Use
/memory(or/mem) in Gemini CLI to interact with loaded context files - View which files are loaded, see their contents, and understand the active context
- Useful for debugging when instructions aren't being followed — check if the file is actually loaded
Patterns That Work
- Keep global GEMINI.md minimal — personal style preferences that apply to all your projects
- Project root GEMINI.md covers stack, conventions, build/test commands
- Subdirectory GEMINI.md files for component-specific or module-specific instructions
- Use
.geminiignoreto prevent scanning directories that don't need context files (build output, node_modules)
Anti-Patterns
- Don't duplicate information available in project files — Gemini can read your code. GEMINI.md is for behavioral instructions, not documentation
- Don't make files too long — all files concatenate into one context block. Quality over quantity
- Don't put secrets or credentials in GEMINI.md — it's a committed file
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 · 45 lines · 0 tokens per session scan A c547ab70145e
gemini-md is a cursor rule published in the GitHub repository nedcodes-ok/cursorrules-collection (37 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 570 tokens. 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.