cx-agentic-ai: Instructions file for Gemini CLI

GEMINI.md

cx-agentic-ai GEMINI.md is an instructions file for Gemini CLI from Checkmarx/cx-agentic-ai. It costs 2,010 tokens per session, scanned A, original, Apache-2.0.

A Gemini CLI instruction file explaining how Checkmarx security hooks and on-demand skills behave. Gemini CLI is a command-line coding assistant.

In plain words
What is it for?
It is for configuring and explaining Checkmarx security checks in Gemini CLI projects.
Why use it?
It documents which file writes and tool calls are checked automatically, which actions are only run on request, and which writes cannot be scanned.

Instructions file for Gemini CLI

Written for Gemini CLI: the file is GEMINI.md. Also seen: mentions Claude Code; mentions Gemini CLI.

This is Checkmarx/cx-agentic-ai's own configuration. It tells Gemini CLI how to work on cx-agentic-ai 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 cx-agentic-ai configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Checkmarx/cx-agentic-ai. 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/Checkmarx/cx-agentic-ai/master/GEMINI.md
Clone the repo
git clone --depth 1 https://github.com/Checkmarx/cx-agentic-ai

Made for: Gemini CLI.

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 cx-agentic-ai GEMINI.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/checkmarx/cx-agentic-ai/gemini-md/github.svg)](https://agentmods.dev/instructions/checkmarx/cx-agentic-ai/gemini-md)
Your own site
<a href="https://agentmods.dev/instructions/checkmarx/cx-agentic-ai/gemini-md"><img src="https://agentmods.dev/badge/instructions/checkmarx/cx-agentic-ai/gemini-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 cx-agentic-ai GEMINI.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/checkmarx/cx-agentic-ai/gemini-md"><img src="https://agentmods.dev/badge/instructions/checkmarx/cx-agentic-ai/gemini-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,010 This file is loaded in full into every session.
When invoked 2,010 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 $0.02010 $0.02010
Opus 5.5 $0.00804 $0.00804
Sonnet 5.5 $0.00402 $0.00402
Haiku 4.5 $0.00201 $0.00201

Measured 1mo ago against content hash 14d33442cce2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cx-agentic-ai 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 1mo 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.

GEMINI.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Checkmarx cx-devassist (Gemini CLI)

This extension provides automatic security hooks and on-demand skills. They serve different purposes — do not conflate them.

Automatic hooks (always on)

BeforeTool hooks run on scannable file writes (WriteFile, write_file, write_.*, replace) and Checkmarx MCP calls (mcp_.*) without skill activation:

  • Gate (cx_check) — proves cx is installed, capable, and authenticated before a scannable write or MCP call proceeds.
  • Scanner (cx hooks gemini-before-file-tool / gemini-before-tool) — scans proposed file content (ASCA/SAST, KICS/IaC, SCA/manifests) or enforces MCP policy.

Shell commands (run_shell_command) are not gated. A single non-blocking observer records OAuth URL/tenant pairs from cx auth login so a later session can offer them — it never blocks.

An AfterAgent lifecycle hook (cx hooks gemini-after-agent) runs at the end of each agent turn for advisory cleanup/telemetry — the Gemini equivalent of Claude Code's Stop → claude-stop. It is non-blocking and does not gate writes or MCP calls.

Writes to file types Checkmarx cannot scan (.md, .css, .sql, .sh, plain .txt, etc.) proceed without the readiness gate. See config/cx-scannable-files and docs/gemini-cli-devassist.md for the full list.

When the user asks you to create, edit, scaffold, or add dependencies as part of normal development — and is not explicitly asking for a security scan or audit:

  • Do not proactively activate cx-devassist-asca, cx-devassist-sca, or cx-devassist-kics. Use the file-write tool directly instead.
  • Scannable files (package.json, requirements.txt, app.py, main.tf, … — see config/cx-scannable-files) are checked by the automatic hook chain: readiness gate first, then native scan of the proposed content. The write is denied if cx is not ready or a real finding is detected.
  • Unscannable files (.md, .css, .sql, .sh, plain .txt, …) are not gated — proceed with the write normally.
  • If a hook denies because cx is missing, outdated, or unauthenticated, activate cx-cli-setup, fix readiness, then retry the same write — do not skip setup and do not activate ASCA/SCA skills instead.
  • If a hook denies because of a security finding, follow the classify-then-act flow below — do not retry the write until every finding in the batch is fixed or ignored, and never ask the developer to choose between remediating and suppressing.

Read the full file on GitHub · 120 lines

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. 1mo ago Changed · +18 lines · +464 tokens per session 14d33442cce2
  2. 1mo ago Changed · +3 lines · +73 tokens per session ae38ae098153
  3. 2mo ago First seen · 99 lines · 1,473 tokens per session scan A 39bc9b53751d

Subscribe to this mod's changes

cx-agentic-ai GEMINI.md is an instructions file published in the GitHub repository Checkmarx/cx-agentic-ai (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 2,010 tokens to every session, about $0.0080 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 2026-09-16.

Related

cx-agentic-ai GEMINI.md compared with instructions from other repositories

cx-agentic-ai GEMINI.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
cx-agentic-ai GEMINI.mdCheckmarx/cx-agentic-aiInstructions file1yesterdayApache-2.0A2,010Gemini CLI
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot
generative-ai-for-beginners AGENTS.mdmicrosoft/generative-ai-for-beginnersInstructions file124ktodayMITA2,981Codex, OpenCode