by ImFeH2
Run tasks and build workflows by talking to Flowent.
# Add to your Claude Code skills
git clone https://github.com/ImFeH2/flowentLast scanned: 7/9/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-07-09T07:46:27.045Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}flowent is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by ImFeH2. Run tasks and build workflows by talking to Flowent. It has 248 GitHub stars.
Yes. flowent passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/ImFeH2/flowent" and add it to your Claude Code skills directory (see the Installation section above).
flowent is primarily written in TypeScript. It is open-source under ImFeH2 on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh flowent against similar tools.
No comments yet. Be the first to share your thoughts!
Run tasks and build workflows by talking to Flowent.
Flowent is an AI workspace built around Steward, an AI operator that helps you run tasks, use tools, and build workflows through conversation. Simple requests can be handled directly by the agent runtime; complex or repeatable work can become workflows that Flowent creates, runs, and refines from execution feedback.
Flowent requires Bubblewrap for local tool isolation and ripgrep for file search. Install the system packages first:
sudo apt-get install bubblewrap ripgrep
Install the CLI globally:
npm install -g flowent
Or install it with pip:
pip install flowent
Start the server:
flowent
Check system requirements:
flowent doctor
Run the server with Docker Compose:
docker compose up
Install dependencies and start the local development server:
sudo apt-get install bubblewrap ripgrep
pnpm install
uv sync --project backend
pnpm dev
You can also run the development container:
docker compose -f docker-compose.dev.yml up