workstreams — security grade SAFE, quality 65/100

Security audit verdict: SAFE · quality 65/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by workstream-labs · Codex Skill · ★ 76

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is workstreams safe to install? View the security audit →

About workstreams

Workstreams An IDE for orchestrating parallel AI coding agents in isolated git worktrees. Run multiple agents on different tasks simultaneously, review their output with inline diff comments, and iterate with a tight feedback loop — all from a single window. Agent-agnostic: works with Claude, Codex, Aider, and more. Download Workstreams is available as a macOS desktop app. Download the latest release — DMG installers for Apple Silicon (arm64) and Intel (x64). Installation Open the .dmg file — Double-click the downloaded DMG. Drag to Applications — Drag the Workstreams icon into the Applications folder. Remove quarantine flag — The app isn't signed with an Apple certificate yet, so macOS will block it. Run: This strips the macOS quarantine flag that causes the misleading "app is damaged" error. Launch Workstreams — Open from Applications. Auto-update is built in. Once installed, the app updates itself on new releases. Features Worktree sidebar with live diff stats The orchestrator sidebar manages multiple git worktrees per repository, showing real-time addition/deletion counts for each.

agent-orchestrationclaude-codeclicodexgit-worktreeparallel-agents

Quick Facts

Stars76
Forks6
LanguageTypeScript
CategoryCodex Skill
Quality Score65.0954091709111/100
Open Issues1
Last Updated2026-04-22
Created2026-03-07
Platformsclaude-code, cli, codex, node
Est. Tokens~6148k

workstreams alternative? Top 6 similar tools

Looking for a workstreams alternative? If you're comparing workstreams with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • garcon by cfal · ⭐ 86

    Self-hosted browser workspace to run coding agents in parallel, steer work as it runs, review diffs, and ship.

  • vnx-orchestration by Vinix24 · ⭐ 61

    Governance-first orchestration for Claude Code, Codex, and Gemini CLI — parallel workers, receipts, quality ga

  • termcanvas by blueberrycongee · ⭐ 379

    An infinite canvas desktop app for visually managing terminals

  • genie by automagik-dev · ⭐ 342

    Wishes in, PRs out. CLI agent that interviews you, plans the work, dispatches parallel agents in isolated work

  • jat by joewinke · ⭐ 251

    The World's First Agentic IDE. Visual dashboard: live sessions, task management, code editor, terminal. Epic S

  • agent-os by saadnvd1 · ⭐ 166

    Mobile-first web UI for managing AI coding sessions (Claude Code, Codex, Aider, Gemini CLI, Amp, Pi). Self-hos

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is workstreams?

workstreams is IDE for parallel AI coding agents. It is categorized as a Codex Skill with 76 GitHub stars.

What programming language is workstreams written in?

workstreams is primarily written in TypeScript. It covers topics such as agent-orchestration, claude-code, cli.

How do I install or use workstreams?

You can find installation instructions and usage details in the workstreams GitHub repository at github.com/workstream-labs/workstreams. The project has 76 stars and 6 forks, indicating an active community.

What are the best alternatives to workstreams?

The top alternatives to workstreams on Agent Skills Hub include garcon, vnx-orchestration, termcanvas. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Codex Skill tools