Code
58 scored tools, ranked by overall score. Last checked on 25 October 2026. Refine with the Finder →
The three to remember
The most installed skill on the official marketplace: one click, immediate effect on UI quality.
- · Utility 9/10, best of the selection
- · Free, no limits
- · No known security caveat
The reference skill for clean React, maintained by the makers of Next.js.
- · Utility 8/10
- · Free, no limits
- · No known security caveat
| Tool | Price | Score | Sec. |
|---|---|---|---|
| Read, Grep, Glob (Claude Code)File reading and project search, without writing. | Free | 8.3 | Security: nothing to flag |
| agent-browser (Vercel)Command-line driven browser for AI agents: accessibility snapshots with stable references (@e1), click, type, and screenshot. | Free | 8.1 | Security: one caveat, see the card |
| shell, apply_patch (Codex)RisingAtomic commands and patches, under dual sandbox and approval control. | Free | 7.9 | Security: serious reservations |
| Edit, Write (Claude Code)Modifying and creating files in the project. | Free | 7.7 | Security: one caveat, see the card |
| E2B Code InterpreterRisingIsolated micro-VM for executing code produced by an agent. | Freemium | 7.3 | Security: one caveat, see the card |
| Outils de l'agent CursorRead, edit, terminal and search from the Cursor agent. | Freemium · from 20 € | 7.3 | Security: one caveat, see the card |
| Outils du GitHub MCPIssues, pull requests, code and security alerts, in read and write mode. | Free | 7.3 | Security: one caveat, see the card |
| run_shell_command, write_file, google_web_search (Gemini CLI)RisingThe built-in tools of Google's CLI, each with confirmation. | Free | 7.2 | Security: one caveat, see the card |
| Bash (Claude Code)Executes shell commands in a persistent session. | Free | 7.1 | Security: serious reservations |
| code_execution (Gemini)Python executed on Google's side, results returned to the model. | Freemium | 7.0 | Security: one caveat, see the card |
| code_execution (Anthropic)Runs Python and bash in an Anthropic sandbox, with a file editor. | Freemium | 6.9 | Security: one caveat, see the card |
| code_interpreter (OpenAI)Executes Python in an OpenAI container, with file input and output. | Paid | 6.8 | Security: one caveat, see the card |
| code_interpreter (Mistral)Python sandbox for Mistral agents. | Paid · from 28 € | 6.7 | Security: one caveat, see the card |
| text_editor (Anthropic)View, create, and replace text in files, client-side. | Free | 6.6 | Security: one caveat, see the card |
| bash (Anthropic, côté client)Claude requests shell commands that your code executes. | Free | 6.4 | Security: serious reservations |
| DaytonaFast-starting sandboxes for agents. | Freemium | 6.1 | Security: one caveat, see the card |
| Modal SandboxesServerless sandboxes with on-demand GPU. | Freemium | 6.1 | Security: one caveat, see the card |
| shell (OpenAI)Shell hosted in a Debian container, network off by default. | Paid | 5.6 | Security: serious reservations |
App : A product you use directly · Tool : A precise action the AI can call · MCP : Standardises the connection between an AI application and systems that expose tools or data · Built-in mode : A feature to switch on inside an assistant you already use (ChatGPT, Claude, Gemini): nothing to install · Skill : A reusable method: instructions, procedures, sometimes scripts or templates · Plugin : A set of capabilities installed into an AI application or a host
Method
Overall score = utility (rated by the editorial team), reliability (GitHub activity, official publisher, reachable site), security (where data goes, permissions, known incidents) and accessibility (install, required level, price), weighted per category. A tool inactive for over six months is flagged and leaves the recommendations. No ranking is sold.
Missing a tool? A score looks wrong?
Write to the editors