Ext Ops Panel
Open dashboard
Comparison

forge vs Codex Subagent

forge is a plugin bundle for AI coding tools published by UtkarshJain98. Marketplaces we read that list it: 1 (Claude Code: claude-plugins-community). Codex Subagent is an MCP server published by parisbs. Marketplaces we read that list it: 1 (Official MCP Registry). As of our marketplace pass on 2026-10-14. This pair was picked by a reader, not by our comparison rule, so search engines are asked not to index the page.

Where each is published

Where each is published
MarketplaceforgeCodex Subagent
Claude Code: claude-plugins-community Listed
Version: 95ef910
Forks (GitHub): 0
Stars (GitHub): 1
Not marked · First seen
Not listed
Official MCP Registry Not listed Listed
Version: 0.5.0
Downloads/month (npm): 1 043
Downloads/week (npm): 49
Forks (GitHub): 0
Stars (GitHub): 0
Not marked · First seen

Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.

The facts side by side

forge vs Codex Subagent
FactforgeCodex Subagent
Marketplaces that list it11
Stars (GitHub) (differs)1 (better)0 (worse)
Forks (GitHub)00
Last releaseNot publishedNot published
Where it runs (differs)Installs as a plugin bundleOn your machine (codex-subagent-mcp)
Transport (differs)Not statedstdio
Tools it declaresNot publishedNot published
Environment variables it asks for (differs)Not published10, secrets among them: 0
Parts of the bundle (differs)1Not a bundle
LicenceNot statedNot stated
Repository (differs)github.com/utkarshjain98/forgegithub.com/parisbs/codex-subagent-mcp
Changes in the last 7 days00
First seen2026-10-112026-10-11

Lines where the two differ have a tinted background and bold values. Where the data itself says which value is better (more marketplaces, a larger figure of the same marketplace, a fresher release, a verified mark on a marketplace that lists both), the better one is also marked green with ▲ and the worse one red with ▼. Where it runs, the transport, the tools, the settings, hooks, the bundle's parts, the licence and the week's changes are marked only as different: more or fewer is not better in itself.

What each says it does

forge

In its own words, on Claude Code: claude-plugins-community:

Description: Adversarial code hardening for Claude Code. Forge spawns two agents — a Builder and a Breaker — that iterate against each other until the code is unbreakable. The Builder implements a feature, the Breaker writes adversarial tests to prove bugs, and the Builder must fix the implementation without deleting or weakening the tests. The loop continues until the Breaker can't produce a failing test. The result is battle-tested code with a permanent adversarial test suite. Key features: - Evidence-based, not opinion-based. Every issue the Breaker raises must have a failing test that proves the bug. No test, no break. This eliminates false positives and subjective feedback. - Iterative adversarial loop. Builder and Breaker are separate agents that go back and forth for up to N rounds. The Builder cannot dismiss feedback; it must make the failing tests pass. - Adversarial tests are permanent. The Breaker's tests stay in the repo under tests/adversarial/ as a regression suite. Future changes are protected

Codex Subagent

In its own words, on Official MCP Registry:

Delegate coding tasks to the OpenAI Codex CLI, installed separately, with explicit model and effort.

How to run each

forge As a Claude Code plugin

Claude Code
/plugin marketplace add anthropics/claude-plugins-community
/plugin install forge@claude-community

Codex Subagent As a local MCP server: npm package

Claude Code
claude mcp add --transport stdio codex-subagent-mcp -- npx -y codex-subagent-mcp

Commands built only from what the marketplaces declare; the full set for every client is on each card.

Tools each declares

Neither one's marketplaces publish a list of tools, so there is nothing to compare.

Settings each asks for

The marketplaces of forge publish no settings it asks for, so we do not compare settings.

What it can do: forge · What it can do: Codex Subagent · Compare two other plugins

Data comes from the public marketplace file https://github.com/anthropics/claude-plugins-community/blob/HEAD/.claude-plugin/marketplace.json. Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.

Where the data comes from: how the catalog is built