Agent Plugins Marketplace
← All plugins

solidforge

v0.1.0

A Loop Engineering system for AI coding agents — one Claude Code plugin. Bundles the converge → specify → implement pipeline plus two additive outcome-axis layers (cited-source verification + uncited-prior-art collision): the cross-source-review, blueprint-crafting, parallel-development, primary-source-verification, and prior-art-search skills; 23 cascaded subagents (plugin-scoped as solidforge:<name>); and the deterministic convergence-loop hooks (fast-gate, blueprint read-only guard, breaker counters). Enable per-project (Layer 1); run /solidforge:arm-tools to provision gate tools + arch-configs + constitution (Layer 2).

Claude Code3 Skills

By solidforge1 GitHub starsUpdated last week

Directory evidence

Runtimes
Claude Code
Parsed components
3 skill or MCP entries
Source updated
Sep 17, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install solidforge for Claude Code

Installs for the current user
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install solidforge@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/maskshell/solidforge

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The repository root is the plugin root.

Plugin files

solidforge/
├── .claude-plugin/plugin.json
├── skills/blueprint-crafting/SKILL.md
├── skills/cross-source-review/SKILL.md
└── skills/parallel-development/SKILL.md

Included Skills3

blueprint-craftingskills/blueprint-crafting/SKILL.md

blueprint-crafting: Produces convergence-checked upstream artifacts — product spec (PRD), architecture design (arch-design), iteration plan, executable summary, and research — that parallel-development consumes as authoritative references. Use it whenever the user wants to author, rewrite, research, or convergence-check an upstream artifact: "author a spec", "write an arch-design", "produce an iteration-plan", "research X for the spec", "spec-driven", "write a PRD", "author a roadmap", "write a design doc", "decision log". Each artifact converges on its constraints-profile (process axis: anchors + authority-chain + sources); content correctness stays human (outcome axis). NOT for implementing code — feature implementation, bug fixes, and refactors route to parallel-development. Specifier half of the specify then implement pipeline.

cross-source-reviewskills/cross-source-review/SKILL.md

cross-source-review — a same-family (同源, fresh-context) + different-family (异源) cross multi-round review engine that drives a doc-shaped artifact to SUBSTANTIVE convergence. Use it when a high-quality document needs adversarial cross-source review to convergence — "cross-review this requirements doc", "converge this design doc", "异源 review this spec/wiki page", "drive 同源+异源 review on this artifact". Produces a converged artifact + an honest convergence-record. NOT for code review (route to parallel-development), spec/arch-design authoring (blueprint-crafting), or research gathering (blueprint-crafting researcher). Does NOT judge whether the doc is "right" (outcome-axis — human). Phase A activation is EXPLICIT invocation (`/cross-source-review`); auto-routing is deferred.

parallel-developmentskills/parallel-development/SKILL.md

Parallel-development orchestrator: runs multiple AI agents in parallel on independent dev tasks. Use it whenever the user wants to implement several features or components at once, work in parallel, do TDD (red-green-refactor, tests first), safely refactor code modules, coordinate backend and frontend simultaneously, or manage multi-agent tasks. Also trigger on "同时做", "并行实现", "test first", "red green refactor", or whenever multiple independent subtasks are identified. Platforms: iOS/Apple (Xcode, Swift, SwiftUI, XCTest, XCUITest, SPM, Simulator); Python (FastAPI, Django, Flask, SQLAlchemy, Pydantic, pytest, poetry, uv, pyproject.toml); Rust (Rust, cargo, Cargo.toml, clippy, rustfmt); Web/frontend (React, Vue, Svelte, TypeScript, JavaScript, Node.js, Express, Next.js, Playwright, ESLint, dependency-cruiser); Java (JDK 17+, Maven, Gradle, JUnit, Checkstyle, google-java-format); Go (Go, golang, go.mod, go vet, golangci-lint, go test). Trigger readily, even without an explicit "parallel" or "TDD" keyword.

Plugin manifests1

.claude-plugin/plugin.json
{
  "name": "solidforge",
  "version": "0.1.0",
  "description": "A Loop Engineering system for AI coding agents — one Claude Code plugin. Bundles the converge → specify → implement pipeline plus two additive outcome-axis layers (cited-source verification + uncited-prior-art collision): the cross-source-review, blueprint-crafting, parallel-development, primary-source-verification, and prior-art-search skills; 23 cascaded subagents (plugin-scoped as solidforge:<name>); and the deterministic convergence-loop hooks (fast-gate, blueprint read-only guard, breaker counters). Enable per-project (Layer 1); run /solidforge:arm-tools to provision gate tools + arch-configs + constitution (Layer 2).",
  "author": {
    "name": "solidforge"
  }
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[solidforge on Agent Plugins Marketplace](https://pluginsmp.com/plugins/solidforge)