SaaSHub helps you find the best software and product alternatives Learn more →
Top 23 Shell codex Projects
-
taste-skill
Taste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop
Project mention: Taste-Skill: The Anti-Slop Framework That Gives Your AI 28.5K⭐ Worth of Taste | dev.to | 2026-05-30npx skills add https://github.com/Leonxlnx/taste-skill
-
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
-
peon-ping
Warcraft III Peon voice notifications (+ more!) for Claude Code, Codex, IDEs, and any AI agent. Stop babysitting your terminal. Employ a Peon today.
-
compose-skill
Jetpack Compose Agent Skill — AI-powered coding guidance with actual androidx/androidx source code receipts. Works with Claude Code, Codex CLI, Gemini CLI, Cursor, Copilot, Windsurf, and more.
Jetpack Compose Expert https://github.com/aldefy/compose-skill This skill provides Claude with real source code and extensive reference guides for Jetpack Compose. Without it, AI tools often misuse remember, generate inefficient recompositions or misorder modifiers; with the skill, Claude picks the right state primitive, applies stability annotations and orders modifiers correctly. The reference guides cover state management, view composition, performance, navigation, animation, lists, side effects, modifiers, theming, accessibility and deprecated patterns. Installation requires cloning the repository and copying the Jetpack Compose expert skill directory into your skills folder; Claude will automatically activate it when you mention Compose or related API names.
-
Aegis
Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks. (by GanyuanRan)
GitHub: https://github.com/GanyuanRan/Aegis
-
turbo-flow
Advanced Agentic Development Environment Supporting Devpods, Rackspace Spot Instances, Github Codespaces, Google Cloud Shell, and more! Features 600+ AI subagents, Claude Flow, SPARC methodology, and automatic context loading! Deploy intelligent multi-agent swarms, coordinate autonomous workflows.
-
Project mention: I Ran Claude Code for 5 Hours and It Burned 26M Tokens. Here's How I Debugged It | dev.to | 2026-03-10
Originally published on Digital Shepard Repo: shepard-obs-stack
-
slot-machine
An open-source skill for running parallel implementations, reviewing them independently, and selecting or synthesizing the best result. (by pejmanjohn)
Project mention: Show HN: /slot-machine development (CC vs. Codex; CE vs. superpowers) | news.ycombinator.com | 2026-03-29 -
orc
A lightweight orchestration framework that piggybacks your local Agentic CLI setup. Intentionally simple. Yet powerful... like an army of Orcs 👹 (by spencermarx)
Project mention: Show HN: Orc – Release the horde. Multi-agent orchestration in pure bash | news.ycombinator.com | 2026-03-19 -
sample-well-architected-skills-and-steering
Reusable skills and steering that teach AI coding agents how to apply the AWS Well-Architected Framework. One set of playbooks, 12 supported tools.
Project mention: Well-Architected Skills and Steering for AI Coding Agents | news.ycombinator.com | 2026-05-26 -
agent-debate
Structured protocol for AI coding agents to debate technical decisions via shared markdown
Project mention: Agent-debate – AI agents review code by editing a shared Markdown file | news.ycombinator.com | 2026-03-11 -
researchclaw-skill
Turn your coding agent into a one-command autonomous research paper generator. Wraps AutoResearchClaw's 23-stage pipeline with setup automation, interactive config, error diagnosis, and self-healing hooks.
Project mention: AutoResearchClaw Tries to Turn One Research Idea Into a Draft Paper | dev.to | 2026-04-26[1] GitHub - aiming-lab/AutoResearchClaw - https://github.com/aiming-lab/AutoResearchClaw
-
Project mention: Show HN: Continue? Y/N: A 60-second game about AI agent permission fatigue | news.ycombinator.com | 2026-05-28
[2] - I built https://github.com/stanislavkozlovski/dclaude/ for this; not perfect but gets my job done on the rare occassion I need to run the coding agent locally
-
5dive
Spawn and manage AI agents that talk to each other. systemd-managed multi-agent runtime on your own VM.
Project mention: Show HN: 5dive – Run a Team of Claude Code Agents from Telegram | news.ycombinator.com | 2026-06-11 -
ag.sh
Command-line ADE tooling to run multiple Claude Code/AI agents in parallel - each in its own isolated git worktree. Spawn, manage, and orchestrate AI-powered development across concurrent tasks without stepping on your own changes.
Project mention: ag.sh – All-in-one CLI tool to do parallelised AI development with ease | dev.to | 2026-04-09ag.sh is a command-line ADE tool to run multiple Claude Code/AI agents in parallel - each in its own isolated git worktree.
-
Project mention: Thousands of CEOs just admitted AI had no impact on employment or productivity | news.ycombinator.com | 2026-02-17
I may use my own skill to automate this... https://github.com/flurdy/agent-skills/blob/main/skills/revi...
-
-
Project mention: Agents-Container Running AI Agents Safely in Docker-in-Docker with GVisor | news.ycombinator.com | 2026-06-11
-
kavro
Think before you build. Universal AI engineering orchestration framework for Claude, Codex, Cursor, and Windsurf.
Project mention: Why AI Coding Agents Fail Senior Engineers (And What I Built to Fix It) | dev.to | 2026-05-20git clone https://github.com/a7medalyapany/kavro.git cd kavro bash scripts/install.sh
-
continue-later-skill
Local handoff skills and CLI for resuming AI coding sessions across Cursor, Claude Code, Codex, Gemini, and OpenCode.
Project mention: Stop losing AI coding context between sessions: Continue Later (skills + CLI) | dev.to | 2026-04-30Check out the source at https://github.com/dhruv-anand-aintech/continue-later-skill
-
Repo: github.com/semiherdogan/agent-poke
-
pst-cli
Secure paste for AI coding agents. Clipboard → macOS Keychain → in-process injection. Zero chat-transcript leakage.
Check out the source and if you like, throw me a ⭐️
-
squirrel-skill
Full-cycle AI coding skill — plans, builds, tests, lints, fixes bugs, and writes production-grade docs. Works on OpenCode, Codex, Claude Code, Cursor, Windsurf, Aider, Cline, and Copilot.
Project mention: I got tired of AI agents trashing my codebase, so I built a skill to fix that | dev.to | 2026-04-27So I spent some time vibe coding a skill file to fix that, and turned it into 🐿️ Squirrel.
-
forgekit
AI dev toolkit for coding agents — rules, skills, and setup for Claude Code, Codex, Cursor, Windsurf, and GitHub Copilot. One command to start.
Project mention: Show HN: Forge Kit – Agent Rules and Skills for Claude Code, Cursor, and Codex | news.ycombinator.com | 2026-05-07
Shell codex discussion
Shell codex related posts
-
Peon-Ping
-
PeonPing: Sound packs for Claude, Codex, Cursor, and other AI coding agents
-
Show HN: A single pane of glass for Claude Code
-
I Ran Claude Code for 5 Hours and It Burned 26M Tokens. Here's How I Debugged It
-
Peon Training feature piggybacks on AI coding session
-
[Github Discoveries] PeonPing: AI Programming with Warcraft III Voice Prompts, Making Claude Code Less Boring
-
A note from our sponsor - SaaSHub
www.saashub.com | 12 Jun 2026
Index
What are some of the best open-source codex projects in Shell? This list will help you:
| # | Project | Stars |
|---|---|---|
| 1 | taste-skill | 25,066 |
| 2 | peon-ping | 4,802 |
| 3 | compose-skill | 502 |
| 4 | Aegis | 251 |
| 5 | turbo-flow | 162 |
| 6 | shepard-obs-stack | 70 |
| 7 | slot-machine | 24 |
| 8 | orc | 19 |
| 9 | sample-well-architected-skills-and-steering | 17 |
| 10 | agent-debate | 14 |
| 11 | researchclaw-skill | 14 |
| 12 | dclaude | 13 |
| 13 | 5dive | 8 |
| 14 | ag.sh | 6 |
| 15 | agent-skills | 4 |
| 16 | codex-starter | 3 |
| 17 | agents-container | 2 |
| 18 | kavro | 2 |
| 19 | continue-later-skill | 1 |
| 20 | agent-poke | 1 |
| 21 | pst-cli | 1 |
| 22 | squirrel-skill | 1 |
| 23 | forgekit | 1 |