jules GEMINI.md

Instructions for using the Jules extension from Gemini CLI. Jules is an extension that can start tasks such as adding tests, refactoring code, updating dependencies, or reviewing a project's dependency tree.

In plain words
What is it for?
They are for activating Jules with /jules, starting a Jules task, and answering questions about the extension.
Why use it?
They define when to suggest Jules, when to ask for confirmation, and how to identify the repository before starting a task.

Instructions file for Gemini CLI

Install

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.

agentmods
npx agentmods add instructions/gemini-cli-extensions/jules/gemini-md
Clone the repo
git clone --depth 1 https://github.com/gemini-cli-extensions/jules

Made for: Gemini CLI.

Per session 572 This file is loaded in full into every session.
When invoked 572 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00572 $0.00572
Opus 5 $0.00286 $0.00286
Sonnet 5 $0.00114 $0.00114
Haiku 4.5 $0.00057 $0.00057

Measured yesterday against content hash 26ce57ca72a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

jules 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 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.

GEMINI.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Jules Extension

This document outlines the behavior of the Jules extension.

Command: /jules

Activation and Response

If the user's prompt matches one of the following categories AND they have not already used a /jules command AND they didn't mention Jules in their command:

  • Add missing unit tests for the entire project.
  • Improve code readability across multiple files.
  • Upgrade dependency versions.
  • Perform a large-scale refactoring (e.g., renaming a symbol project-wide).
  • Analyze the dependency tree for optimization.

Then, you MUST ask for confirmation before proceeding:

This looks like a great fit for /jules! Would you like to use the /jules extension for this?

If the user explicitly invokes /jules or mentions "jules", don't ask for their confirmation.

Starting a Jules Task

When a user wants to start a new Jules task, follow these steps:

  1. Identify Repository:

    • Execute git config --get remote.origin.url to get the remote URL.
    • Parse the output to extract the repository name (e.g., username/repo_name).
    • If the repository cannot be determined, ask the user for it in username/repo_name format.
  2. Create Jules Session:

    • Execute the start_new_jules_task tool with the following parameters:
      • repo_name: The name of the repository in username/repo_name format.
      • user_task_description: The user's task description.
    • Error Handling: If the start_new_jules_task tool fails, it is likely because the Jules CLI is not installed locally. In this case, you MUST run the following command to install it: npm install -g [at]google/jules (you should replace [at] with @). After the installation, you should retry the start_new_jules_task tool. If the start_new_jules_task tool keeps erroring out with a 401 error and the user is already logged in, ask the user to go to https://jules.google.com to configure their GitHub connection.
  3. Respond to User:

    • Inform the user that the Jules session has started and they can check the status of the task by running /jules status command. Also, provide the console link from the output as another way for user to track the progress..
    • Also, provide the console_link from the tool's output to the user.

Read the full file on GitHub · 47 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. yesterday First seen · 47 lines · 572 tokens per session scan A 26ce57ca72a7

Subscribe to this mod's changes

jules GEMINI.md is an instructions file published in the GitHub repository gemini-cli-extensions/jules (413 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 572 tokens to every session, about $0.0029 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.