← Back to Skills Marketplace
ajstafford

Jules CLI

by Andrew Stafford · GitHub ↗ · v1.0.2
cross-platform ✓ Security Clean
2132
Downloads
1
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install jules-cli
Description
Interact with the Jules CLI to manage asynchronous coding sessions. Use this skill sparingly for complex, isolated tasks that benefit from a remote VM.
README (SKILL.md)

Jules CLI Skill

Overview

This skill enables the agent to interact with the jules CLI. It supports task assignment, session monitoring, and result integration.

Usage Guidelines (CRITICAL)

To prevent excessive and inappropriate session creation, you must follow these rules:

  1. Local First: If you can solve the task locally within your current environment (e.g., editing files, running tests, small refactors), do not use Jules.
  2. Complexity Threshold: Only use Jules for tasks that are:
    • Large-scale: Touching many files or requiring significant architectural changes.
    • Isolated: Benefiting from a clean, remote environment to avoid local dependency issues.
    • Exploratory: Tasks where the solution isn't immediately obvious and requires iteration in a VM.
  3. No Proliferation (One at a Time):
    • Never create multiple sessions for the same task.
    • Never use a loop or parallel execution to spin up several sessions at once.
    • Wait for a session to complete and inspect the results before deciding if another session is needed.
  4. No "Small" Tasks: Do not submit tasks like "Add a comment", "Change a variable name", or "Fix a typo".

Security Guidelines

To ensure safe execution of CLI commands, you must adhere to the following security practices:

  1. Input Validation: Before running any command, validate that:
    • Repository names follow the owner/repo format (alphanumeric, dots, hyphens, and underscores).
    • Session IDs are alphanumeric (typically hyphens and underscores are also allowed).
  2. Quoting: Always wrap shell placeholders in double quotes (e.g., "\x3Crepo>").
  3. No Inline Injection: Never embed user-provided data directly into script strings (like python3 -c). Use environment variables to pass such data safely.
  4. Sanitization: Ensure task descriptions do not contain malicious shell characters if passed directly to the shell.

Safety Controls

  • Approval Required (MANDATORY): You must ask for explicit user approval before running any of the following commands:
    • jules remote new: Since this creates a remote session/VM.
    • jules remote pull --apply: Since this modifies the local codebase.
    • jules teleport: Since this clones and modifies the environment.
  • Verification: Always run jules remote list --session before creating a new one to ensure you don't already have a pending session for the same repository.
  • Credentials: If jules login is required, explain why to the user and wait for their confirmation before proceeding.

Core Workflow (Manual Control)

Prefer using the CLI directly to maintain situational awareness.

1. Pre-flight Check

Verify repository access and format.

jules remote list --repo

Note: Ensure the repo format is GITHUB_USERNAME/REPO.

2. Submit Task

Create a session and capture the Session ID.

# Capture the output to get the ID
# Replace \x3Crepo> and task description with validated inputs
jules remote new --repo "\x3Crepo>" --session "Detailed task description" \x3C /dev/null

3. Monitor Progress

List sessions and look for your ID. Use this robust one-liner to check the status (it handles statuses with spaces like "In Progress"):

Check Status (Safe Method):

# Use an environment variable to pass the Session ID safely to Python
export JULES_SESSION_ID="\x3CSESSION_ID>"
jules remote list --session | python3 -c "
import sys, re, os
session_id = os.environ.get('JULES_SESSION_ID', '')
if not session_id: sys.exit(0)
for line in sys.stdin:
    line = line.strip()
    if line.startswith(session_id):
        # Extract status (the last column after multiple spaces)
        print(re.split(r'\s{2,}', line)[-1])
"
unset JULES_SESSION_ID

4. Integrate Results

Once the status is Completed, pull and apply the changes.

# Replace \x3CSESSION_ID> with the validated Session ID
jules remote pull --session "\x3CSESSION_ID>" --apply \x3C /dev/null

Error Handling & Troubleshooting

  • Repository Not Found: Verify format with jules remote list --repo. It must match the GitHub path.
  • TTY Errors: Always use \x3C /dev/null for non-interactive automation with the raw jules command.
  • Credentials: If you see login errors, ensure HOME is set correctly or run jules login.

Command Reference

Command Purpose
jules remote list --repo Verify available repositories and their exact names.
jules remote list --session List active and past sessions to check status.
jules remote new Create a new coding task.
jules remote pull Apply changes from a completed session.
jules teleport "\x3Cid>" Clone and apply changes (useful for fresh environments).
Usage Guidance
This skill is an instruction-only guide for using a separate Jules CLI tool; it does not install software or ask for secrets. Before installing/using it: (1) ensure you have a trusted `jules` binary on your system (the skill assumes the CLI is already present), (2) confirm your agent will prompt you for approval before creating or applying remote sessions (the SKILL.md requires this), and (3) avoid sending sensitive data in session descriptions or commands — treat sessions as potentially visible to the remote VM/service. If the publisher later adds an install step (downloading a binary) or starts requesting API keys/credentials, re-evaluate — that would change this assessment.
Capability Analysis
Type: OpenClaw Skill Name: jules-cli Version: 1.0.2 The skill provides powerful capabilities for remote code execution and modification via the `jules` CLI. However, the `SKILL.md` file includes exceptionally robust security guidelines and mandatory safety controls for the AI agent. These include explicit instructions for input validation, proper quoting, avoiding inline injection (demonstrated by using environment variables for `python3 -c`), and critically, mandatory user approval for all high-impact commands like `jules remote new`, `jules remote pull --apply`, and `jules teleport`. There is no evidence of intentional malicious behavior, data exfiltration, or obfuscation; instead, the documentation actively mitigates common security risks.
Capability Assessment
Purpose & Capability
The skill's name/description match the SKILL.md: it instructs how to run the `jules` CLI and uses `python3` for lightweight parsing. It does not request unrelated binaries, credentials, or config paths.
Instruction Scope
The runtime instructions stay on-topic (creating/listing/pulling remote sessions) and include explicit safety rules (input validation, quoting, using env vars, asking user approval before sensitive commands). Note: these safety controls rely on the agent obeying them — the SKILL.md mandates asking user approval before `jules remote new`, `jules remote pull --apply`, and `jules teleport`.
Install Mechanism
No install spec or code files are present (instruction-only). Nothing is downloaded or written to disk by the skill itself.
Credentials
No required environment variables or credentials are declared. The instructions reference HOME and use a transient env var (JULES_SESSION_ID) for safe shell interaction, which is proportionate to the task.
Persistence & Privilege
The skill is not forced always-on and does not persist credentials. Model-invocation is allowed (platform default). Because the SKILL.md requires explicit user approval for session-creating/modifying commands, confirm the agent will actually prompt before executing those commands if you want that protection enforced.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install jules-cli
  3. After installation, invoke the skill by name or use /jules-cli
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.2
- Added a security guidelines section detailing safe command practices, including input validation, quoting, and sanitization. - Required explicit user approval before running sensitive commands like session creation, applying changes, and teleporting. - Updated usage examples to use validated and safely quoted inputs with environment variable handling for session IDs. - Declared required binaries (jules, python3) and environment variable (HOME) in the skill metadata. - Clarified credential instructions and user notification requirements.
v1.0.1
**Summary:** Removes bundled automation scripts and shifts the skill towards stricter, manual, and controlled usage. - Removed bundled helper scripts: jules_submit.py, parse_sessions.py, and wait_for_session.sh. - Updated documentation to emphasize manual CLI workflows instead of scripted automation. - Added critical usage guidelines restricting Jules to complex, isolated, or exploratory tasks only. - Introduced safety controls: session proliferation prevention and approval requirements for unclear cases. - Clarified troubleshooting steps and command-line usage patterns.
v1.0.0
Initial release of jules-cli skill. - Enables interaction with the Jules CLI to manage asynchronous coding sessions. - Provides automated and manual workflows for submitting, monitoring, and applying task results. - Includes detailed guidance for verifying repository access and handling common authentication/TTY errors. - Supplies scripts for automated task submission (`jules_submit.py`) and session monitoring. - Documents key commands and workflows for reproducible, TTY-safe automation.
Metadata
Slug jules-cli
Version 1.0.2
License
All-time Installs 0
Active Installs 0
Total Versions 3
Frequently Asked Questions

What is Jules CLI?

Interact with the Jules CLI to manage asynchronous coding sessions. Use this skill sparingly for complex, isolated tasks that benefit from a remote VM. It is an AI Agent Skill for Claude Code / OpenClaw, with 2132 downloads so far.

How do I install Jules CLI?

Run "/install jules-cli" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Jules CLI free?

Yes, Jules CLI is completely free (open-source). You can download, install and use it at no cost.

Which platforms does Jules CLI support?

Jules CLI is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Jules CLI?

It is built and maintained by Andrew Stafford (@ajstafford); the current version is v1.0.2.

💬 Comments