A zero-dependency CLI tool to quickly rename, list, or auto-generate friendly, randomized labels for OpenClaw-style agent sessions.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install rename-session
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install rename-session using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
The Rename Session skill is a minimal, zero-dependency Python utility designed to manage, list, and modify session labels directly inside the configuration files of your AI agents. Acting on the OpenClaw-style layout, it integrates perfectly into workflows utilizing Openclaw Skills.
By editing configuration paths seamlessly, it modifies the sessions.json metadata file instantaneously to let developers and operators easily identify various execution states or conversation threads. The tool supports literal renaming, listing, and intelligent random label generation with multi-agent auto-detection and locale-aware features, keeping your workspace clean and organized without adding unnecessary overhead.
--agent.sessions.json or locates the specific session_key provided in the CLI argument.--random flag is used, it applies a locale-aware random generator to assemble a formatted label (sessions.json file. It then runs a verification check to ensure the file was correctly written and the changes are active. It also logs the output to an XDG-compliant history file to avoid immediate label repetition.To set up and run the Rename Session tool within your system, ensure you have Python 3 installed. No external packages are required.
# Clone the repository containing the skill
git clone https://github.com/Songhonglei/better-agent-skills
cd better-agent-skills
# List all active sessions
python3 scripts/rename_session.py --list
# Rename a specific session
python3 scripts/rename_session.py agent:main:main 'Feature Implementation Phase' --agent main
You can configure the environment to customize search paths for Openclaw Skills setups:
# Override the default agents root path
export RENAME_SESSION_ROOT='/path/to/custom/agents'
# Define XDG compliance path for label history
export XDG_DATA_HOME='~/.local/share'
The tool manages session metadata directly in the OpenClaw workspace directory structure. It expects files organized under the following schema:
~/.openclaw/agents/
└── <agent-id>/
└── sessions/
└── sessions.json
To prevent immediate label repetition when generating randomized labels, the utility tracks history under $XDG_DATA_HOME/rename-session/history.json. It maintains a list of the last 10 assigned labels:
| Attribute | Description | Location |
|---|---|---|
| sessions.json | The primary session database modified by this tool. | |
| history.json | Stores recent random labels to avoid repetition. | ~/.local/share/rename-session/ |
This schema ensures lightweight local persistence without external database systems, aligning with standard practices for Openclaw Skills.
$LANG or $LC_ALL) to generate appropriate Chinese or English random strings, or allows explicit setting via --lang.Loading
A multi-language static code security audit tool designed to detect over 60 regex-based vulnerability patterns across PHP, Java, Python, and Go.

A zero-dependency, local-first utility to instantly broadcast and update memory notes across multiple AI agent workspaces.

SymSkill enables AI agents to execute complex, multi-branch instructions sequentially and faithfully with dynamic execution flows.

A comprehensive demonstration skill designed to streamline automated publishing, version management, and changelog tracking on the ClawHub platform.

A real-time currency conversion skill that fetches live exchange rates from Open Exchange Rates via a local Python script execution.

An AI-powered document and workflow generator for early childhood educators, producing interactive, visually appealing HTML reports based on national learning guidelines.








































