SkillAgentSearch skills...

forge

Go + React framework and CLI that builds, runs and ships static sites, SPAs, web/mobile apps and Go APIs (Connect RPC, protobuf, SQL migrations, generated ORM/handlers/hooks/tests), with linters for agent-written code. Deploys to hosted infra, Kubernetes, Docker Compose or host processes.

Install / Use

claude mcp add reliant-labs -- npx -y github:reliant-labs/forge

If the server publishes to npm under a different name, use that package instead — check the repo README.

About this skill
🔌

MCP Server

Model Context Protocol server

Quality Score

84/100

Category

Operations

Supported Platforms

Claude Code
Claude Desktop
Cursor
Gemini CLI

Our assessment of forge

forge scores 84/100 on our quality scale, 546th of 745 Operations skills we index.

Its MCP Server is 17 KB long, well organised into 19 sections with 11 code examples: a thorough specification that gives an agent plenty to work with.

It has 10 GitHub stars, so there is little community track record yet; judge it on its content.

Substance
30/30
Structure
20/20
Description
15/15
Adoption
4/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated yesterday, so forge is actively maintained.
  • It is released under the Apache-2.0 license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 97/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands (3 minor notes below). An AI review of the same text found nothing harmful.

  • noteInstalls by piping a downloaded script into a shellline 51
    curl -fsSL https://raw.githubusercontent.com/reliant-labs/forge/main/install.sh | sh
  • noteInstalls by piping a downloaded script into a shellline 245
    curl -fsSL https://raw.githubusercontent.com/reliant-labs/forge/main/install.sh | sh
  • noteInstalls by piping a downloaded script into a shellline 250
    irm https://raw.githubusercontent.com/reliant-labs/forge/main/install.ps1 | iex

AI review by kimi-k2.7-code on 2026-11-13. Automated pattern scan on 2026-11-13. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

forge compared with similar skills

All 4 of these similar skills score higher than forge; compare them before choosing.

SkillScoreStarsUpdatedFormat
forge (this skill)by reliant-labs84101d agoMCP Server
claude-memby thedotmack100117.6ktodayCLAUDE.md
Agent-Reachby Panniantong100112.3k8d agoCLAUDE.md
rufloby ruvnet10081.9ktodayCLAUDE.md
headroomby headroomlabs-ai10079.8ktodayCLAUDE.md

Frequently asked questions

How do I install forge?
Run claude mcp add reliant-labs -- npx -y github:reliant-labs/forge. The install tabs above show the steps for each supported agent.
Which AI agents does forge work with?
It is written for Claude Code, Claude Desktop, Cursor and Gemini CLI, as a MCP Server file. Other agents that read the same format can often use it too.
Is forge safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands (3 minor notes below). An AI review of the same text found nothing harmful. It is Apache-2.0-licensed and scores 97/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is forge still maintained?
The repository was last updated yesterday, so forge is actively maintained.

Forge

Forge is an opinionated, open-source Go + React framework and deploy platform that ships the production system — dev environments, tests, secrets, multiple environments, releases, observability and hosting — from the first commit, built for AI agents to work in.

The Go framework for AI-generated code, with an MCP server that deploys your app:

# Deploy a Vite or Next.js static app without an account (live URL + 72-hour claim link)
npx -y @reliantlabs/forge@latest env deploy prod --claimable

# Use from your agent: an MCP server to deploy your app (Claude Code; Cursor, Codex and Gemini below)
claude mcp add forge -- npx -y @reliantlabs/forge mcp

# Not sure where to start? forge start prints the one next command for this directory
forge start

Install forge, and the other ways to run it: Install.

<p align="center"> <a href="https://reliantlabs.io/products/forge">Website</a> · <a href="https://demo.reliantlabs.io/forge/demo?section=built">Live demo</a> · <a href="https://docs.reliantlabs.io/forge/overview">Docs</a> · <a href="https://github.com/reliant-labs/reliant">Reliant</a> · <a href="https://join.slack.com/t/reliant-pn51441/shared_invite/zt-4c7wet6o2-W_Tksw80LaRGxZqUz9GQdA">Slack</a> </p> <p align="center"> <a href="https://github.com/reliant-labs/forge/releases/latest"><img alt="Latest release" src="https://img.shields.io/github/v/release/reliant-labs/forge" /></a> <a href="LICENSE"><img alt="License: Apache-2.0" src="https://img.shields.io/badge/license-Apache--2.0-blue" /></a> <a href="https://www.npmjs.com/package/@reliantlabs/forge"><img alt="npm" src="https://img.shields.io/npm/v/@reliantlabs/forge" /></a> </p>

Most teams build that system in year two, under deadline, on top of a codebase that wasn't shaped for it. With Forge the first commit already has it, wired into files you own and can change.

Try it in the browser first: the live demo.

Quick start

# Install (macOS / Linux; Windows, Homebrew, npm and go install: see Install below)
curl -fsSL https://raw.githubusercontent.com/reliant-labs/forge/main/install.sh | sh

forge project new my-app && cd my-app
forge scaffold service billing
forge generate
forge env up dev

That last command brings up Postgres, runs your migrations, and starts your services and frontends, then prints a table of URLs and a log file for each process, including the HyperDX UI, already receiving the app's traces, metrics and logs. With a frontend (forge project new my-app --frontend web) it also starts a local identity provider, so the app's own sign-in page works on the first run. No signup, no external accounts, no cloud project, no cluster.

Add tables (a // forge:entity message and forge scaffold) and a fresh database is seeded with foreign-key-coherent rows that satisfy every constraint your schema declares, so the app boots alive instead of empty.

When you want it online, forge env deploy staging builds a release once and deploys it. A new project's staging and prod are bound to Reliant hosting; the same environments deploy to a Kubernetes cluster you run, or as host processes, by changing where each workload is bound. Before you call a change done: forge generate && forge lint && go build ./... && task test.

Everything included

What a new app would otherwise stitch together from separate tools:

<!-- benefits:start -->

| | What you get | | -------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Build | One marker, a whole entity · Proto in, full stack out | | Data | SQL migrations are the schema · Migration safety checks | | Test | Real Postgres in every test · A generated mock per interface | | Dev | The whole stack, one command · A dev stack per worktree | | Guardrails | Bug-class linters, one verdict · The whole CI gate, locally | | Security | Auth that fails closed · Errors never leak internals · Secrets never in git · Dependency and image scanning · Signed images, SBOM and provenance | | Ship | Build once, promote by digest · Deploy anywhere, declare once | | Host | Managed Postgres · Static hosting with a CDN · Custom domains with automatic HTTPS | | Run | Observability stack included · Production alerts out of the box · Prove each deploy is good | | Agents | Skills that match your forge · Built-in MCP server |

Every benefit, with how to use it and the code that backs it: docs/benefits.md

<!-- benefits:end -->

Add Reliant and the list grows an agent harness, cloud dev machines, AI code and security review, and an on-call agent. Forge doesn't need any of them.

Built for your agent

When an agent writes most of the code, the bottleneck stops being how fast you can write it and becomes knowing whether it's right. Forge is one binary on your PATH with no plugin, editor extension or server, so anything that can run a shell command can drive it: Claude Code, Codex, Cursor, Copilot, Gemini CLI, Aider, a harness you wrote, or a CI job. A person at a terminal uses the same commands, so there is nothing an agent can do that you can't check by hand.

  • Skills live in the binary. forge skill search <topic> and forge skill load <name> print the playbook for an area, about 150 of them, matched to the installed version. Nothing to paste into a prompt, nothing to drift.
  • It explains itself. forge start prints the one command for the directory you are in (deploy the app already there, or create one), and forge start app the path from an empty directory to authored protos. forge project capabilities --json lists every verb, lint analyzer and marker, enumerated from the binary, so it can't go stale.
  • Scaffolding and lints are guardrails against AI slop. forge scaffold lands each service, rpc, worker or entity in the right place, already wired. forge lint rejects what review misses, names the file, line, rule and fix, and forge lint --quiet ends with the verdict, so the agent reads one line to know whether it is done.
  • It debugs from real telemetry. forge obs status, forge obs issues and forge obs trace read a running app's logs, traces, errors and alerts, so a fix starts from what happened rather than a guess.
  • Checks never fake a pass. A check that cannot obtain its facts reports UNDETERMINED, never green, never skipped.
  • The project tells the agent all of this. forge project new writes AGENTS.md and a pointer for the agent it detects (Claude Code, Cursor, Copilot). Any MCP-capable harness can run forge mcp instead: see Use as an MCP server.

To use Forge from any agent, put this in the prompt or its instructions file:

Use Forge (github.com/reliant-labs/forge) for this project.
Run `forge start` first and follow it. Load depth with
`forge skill search <topic>` and `forge skill load <name>`.
A change is done when `forge lint`, `go build ./...` and `task test` pass.

Use as an MCP server

<a href="https://cursor.com/en/install-mcp?name=forge&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsIkByZWxpYW50bGFicy9mb3JnZSIsIm1jcCJdfQ=="><img alt="Add forge to Cursor" src="https://cursor.com/deeplink/mcp-install-dark.svg" height="32" /></a> <a href="https://insiders.vscode.dev/redirect/mcp/install?name=forge&config=%7B%22command%22%3A%22npx%22%2C%22args%22%3A%5B%22-y%22%2C%22%40reliantlabs%2Fforge%22%2C%22mcp%22%5D%7D"><img alt="Install forge in VS Code" src="https://img.shields.io/badge/VS_Code-Install_forge-0098FF?logo=visualstudiocode&logoColor=white" height="32" /></a>

forge mcp serves forge over the Model Context Protocol on stdio. It is in the official MCP registry as io.github.reliant-labs/forge, and npx runs it with nothing to install, no API key and no config. For Claude Code:

claude mcp add forge -- npx -y @reliantlabs/forge mcp

Or commit a .mcp.json to the project (Cursor reads the same shape from .cursor/mcp.json):

{
  "mcpServers": {
    "forge": {
      "command": "npx",
      "args": ["-y", "@reliantlabs/forge", "mcp"]
    }
  }
}

For Codex (CLI, IDE extension and desktop app share the config):

codex mcp add forge -- npx -y @reliantlabs/forge mcp

or in ~/.codex/config.toml (or a trusted project's .codex/config.toml):

[mcp_servers.forge]
command = "npx"
args = ["-y", "@reliantlabs/forge", "mcp"]

For Gemini CLI, this repository is an extension (gemini-extension.json):

gemini extensions install https://github.com/reliant-labs/forge

deploy_claimable puts a Vite app or a Next.js static export live with no account and returns its URL plus a claim link that is good for 72 ho

Truncated for display — read the full file on GitHub.

Related Skills

View on GitHub
GitHub Stars10
CategoryOperations
Updated1d ago
Forks2

Languages

Go

Trust signals

97/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

1 info
forge — MCP Server: Install & Safety Check | SkillAgent