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/gemini-cli-extensions/google-secops/gemini-mdgit clone --depth 1 https://github.com/gemini-cli-extensions/google-secopsWhat 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 | $0.01356 | $0.01356 |
| Opus 5 | $0.00678 | $0.00678 |
| Sonnet 5 | $0.00271 | $0.00271 |
| Haiku 4.5 | $0.00136 | $0.00136 |
Grade B, and why
google-secops GEMINI.md scanned grade B 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
5. **Enable Skills**: Ensure your `~/.gemini/settings.json` has `experimental.skills` enabled: How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google SecOps Extension
This repository contains the Google SecOps Extension, providing specialized skills and tools for security operations.
This is not an officially supported Google product.
This project is not eligible for the Google Open Source Software Vulnerability Rewards Program.
Overview
This extension packages setup and key security workflows into skills.
Crucially, it automatically configures the Google Cloud Remote MCP Server for SecOps. This means:
- No Local Tools: You don't need to install or manage local Python environments for standard tools.
- Enterprise Ready: Connects directly to Google's managed infrastructure for SecOps.
- Adaptive: While it defaults to the Remote server, it can fallback to local tools if needed.
Prerequisites
-
Install Gemini CLI (Preview):
npm install -g @google/gemini-cli@preview -
Google Cloud Authentication: Ensure you are authenticated with Google Cloud and have set a quota project:
gcloud auth application-default login gcloud auth application-default set-quota-project <YOUR_PROJECT_ID> -
Enable MCP Service: You must enable the Chronicle MCP service in your Google Cloud project:
gcloud beta services mcp enable chronicle.googleapis.com/mcp --project=<YOUR_PROJECT_ID> -
GUI Login Requirement: You MUST have logged into the Google SecOps GUI at least once before using the API/MCP server.
-
Enable Skills: Ensure your
~/.gemini/settings.jsonhasexperimental.skillsenabled:{ "security": { "auth": { "selectedType": "gemini-api-key" } }, "general": { "previewFeatures": true }, "experimental": { "skills": true, "extensionConfig": true } }
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 · 151 lines · 1,356 tokens per session scan B 7454503e37e8
google-secops GEMINI.md is an instructions file published in the GitHub repository gemini-cli-extensions/google-secops (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,356 tokens to every session, about $0.0068 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
notfair-plugin AGENTS.md
AGENTS.md instructions for nowork-studio/notfair-plugin, covering notfair — skill resolver for ai agents, how to use this file, seo, paid ads and analytics.
Agentkey AGENTS.md
Instructions for chainbase-labs/Agentkey, covering agents.md, what this repo is, directory structure, key commands and test a local edit against every detected agent.
domscribe CLAUDE.md
Instructions for patchorbit/domscribe, covering claude.md, what is domscribe?, how to work on this codebase, commands and install dependencies (pnpm, not npm).
mcp-server-tauri GEMINI.md
Instructions for hypothesi/mcp-server-tauri, covering tauri mcp cli, core workflow, critical failure modes and skill.
bookstack-mcp CLAUDE.md
Instructions for ttpears/bookstack-mcp, covering claude.md, project overview, build & development commands, architecture and configuration.
logic-lens GEMINI.md
Instructions for hyhmrright/logic-lens, covering logic-lens — developer guide (gemini cli), invoking skills, installation, project layout and key conventions.