agent-install standardizes skills, MCPs across agents

// 50d agoOPENSOURCE RELEASE

agent-install standardizes skills, MCPs across agents

agent-install is an open-source CLI and Node API for installing skills, MCP servers, and AGENTS.md content across multiple coding agents. The repo targets a fragmented setup problem by writing each agent’s native config instead of forcing one brittle format.

// ANALYSIS

This is infrastructure for the AI coding stack, not another agent. The real value is reproducibility: teams can stamp the same capabilities across Claude Code, Cursor, Codex, OpenCode, and other agents without manual drift.

–Supports both one-off CLI usage and programmatic installs, so it fits local workflows and CI/CD automation
–Writes to native surfaces like skills directories, MCP JSON/JSONC/YAML/TOML, and AGENTS.md variants
–Makes multi-agent setups less error-prone by centralizing install logic in one tool
–Strong fit for teams standardizing tool access across editors, terminals, and internal agent fleets
–Open-source release lowers adoption friction, but it also puts config hygiene and security review back on the user

// TAGS

agent-installapiclimcpautomationdevtoolopen-sourcecoding-agentai-coding

DISCOVERED

50d ago

2026-05-01

PUBLISHED

50d ago

2026-05-01

RELEVANCE

8/ 10

AUTHOR

aidenybai

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

VIDEO57m ago

Claude Code, Bun creators demo autonomous loops

This 20-minute talk by Boris Cherny (Head of Claude Code at Anthropic) and Jarred Sumner (creator of Bun) details their transition from manual coding to fully autonomous developer workflows. They showcase "RoboBun," an agentic setup using Claude Code to reproduce issues, generate regression tests, and manage pull requests, illustrating how developers are shifting from simple chatbot prompts to multi-agent parallel loops for code maintenance.

MODEL1h ago

Gemma 4 12B Fable 5 Composer 2.5 drops

Gemma 4 12B Agentic Fable 5 Composer 2.5 is a community-developed fine-tune of Google's Gemma 4 12B instruct model, optimized for local coding, tool use, and multi-step agentic workflows. Leveraging distilled reasoning traces, the model claims a 3.5x improvement over the base model on local telecom benchmarks, bringing high-fidelity reasoning capabilities to local developer setups.

NEWS2h ago

Givros asks if GPT-5.6 hits OpenAI Codex

AI creator Givros publicly asked OpenAI's Head of Codex Thibault Sottiaux whether the rumored GPT-5.6 model will be integrated into the Codex coding agent platform immediately upon its release. The question underscores the intense community interest in how quickly OpenAI will roll out new model capabilities to its developer tools amidst rumors of GPT-5.6's testing and impending launch.

agent-install standardizes skills, MCPs across agents