47,133 repositories indexed
1–22 of 22 · Most stars
Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.
An interactive command-line HTTP and API testing client built on top of HTTPie featuring autocomplete, syntax highlighting, and more. https://twitter.com/httpie
⛔️ DEPRECATED Material Design tap target for Android. https://sjwall.github.io/MaterialTapTargetPrompt/
Bash prompt with colors, git statuses, and git branches.
Ultra-pure, lag-free prompt with async Git status—just for Fish
Powerline-style Bash prompt in pure Bash script. See also https://github.com/riobard/zsh-powerline
The foundation layer for agentic intelligence.
Lightweight Claude Code statusLine: 5h/7d rate-limit usage, reset countdowns, model + context window, prompt-cache age — one line, 3 styles × 9 themes, daemon fast-mode
bash prompt with GIT, SVN and HG modules
Access control for AI agents. Set what Claude Code, Codex, Gemini, Cursor and any MCP server are allowed to do, review risky actions before they run, and keep every action on the record.
Color, ASCII-only Git prompt for zsh, bash, ksh93, mksh, pdksh, oksh, dash, yash, busybox ash, and osh
In the midst of all the tools out there that you can possibly use to keep track of them. Here's a "shovel" that just works to try them all out.
Karpathy-inspired coding-agent guidelines packaged for Claude Code, Codex, Cursor, Gemini, OpenCode, Aider, Copilot, OpenClaw, and any AGENTS.md or Agent Skills-compatible agent.
An interactive command-line InfluxDB cli with auto completion.
📍Add git-prompt-string to your Neovim statusline!
Agent Skills — agent-neutral autonomous product-building OS for 32+ AI coding tools. 23 skill categories · 28 agents · 149 reference docs · 37 platform variants. One-line prompts → deployed products on Cloudflare Workers.
A repo-native coding-agent loop harness for Claude, Codex, Copilot, and other CLI agents. Agents can edit. Gates decide what lands. You set the plan in motion. The agents take a prompt, and each iteration must update specs and commit through guardrails.
Prompt-injection firewall for LLM applications — 33 input detectors, 9 output scanners, federated ed25519-signed threat-intel feed. Apache 2.0, 1040 tests, F1 96.0% with 0% false positives. Docker, GitHub Action, LangChain/LlamaIndex/CrewAI integrations.
The prettiest statusline for Claude Code — pure bash, never blocks your prompt. Usage quota, context window, git status & more.
A CodeCompanion extension for using VS Code Copilot prompts and Chat Mode prompts
Cross-platform TokRepo search skill for Claude Code, Codex, Cursor, Gemini CLI, and AGENTS-compatible tools.
Agent-native MCP server for TokRepo discovery, install planning, safe install, and reusable asset publishing.