module-pipeline
v0.3.0Spec-driven multi-agent pipeline: a Main Architect splits a spec into module folders with one owner each, module agents implement them in parallel isolated worktrees under enforced write scopes, every accepted module is committed on a per-run branch, reviewers gate each stage, and rework runs close the loop.
By NeroLicense: MIT0 GitHub starsUpdated 1 hour ago
Directory evidence
- Runtimes
- Claude Code
- Parsed components
- 7 skill or MCP entries
- Source updated
- Sep 28, 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 module-pipeline for Claude Code
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install module-pipeline@agent-plugin-marketplacePaste 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/spardanviro/MultiAgentGameStudioClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/module-pipeline/.
Plugin files
├── .claude-plugin/plugin.json├── skills/clean/SKILL.md├── skills/finish/SKILL.md├── skills/integrate/SKILL.md├── skills/plan/SKILL.md├── skills/rework/SKILL.md├── skills/run/SKILL.md└── skills/status/SKILL.md
Included Skills7
Remove module-pipeline leftovers - worktrees kept for inspection, stale worktree claims, merge worktrees, and (optionally) run branches already merged into the main branch.
Wrap up a module-pipeline run - summarize the run branch against the main branch, draft a PR description, and merge or open a PR only with the user's explicit yes.
After every module is merged, write the integration glue in an isolated worktree, commit it on the run branch, run diagnostics, and review the whole system against the spec.
Act as the Main Architect - turn a finished implementation spec into module folders, contracts, per-module prompts and a validated task manifest for /module-pipeline:run.
Act as the Main Architect on a finished run - decide every failure and blocking review item, and write the next run's manifest and prompts.
Implement every pending module of a task manifest in parallel isolated worktrees, commit in-scope work on the run branch, review each module, and report the gate.
Show module-pipeline runs in this project - task outcomes, diagnostics, open worktree claims, and the suggested next step.
Plugin manifests1
{
"name": "module-pipeline",
"displayName": "Module Pipeline",
"version": "0.3.0",
"description": "Spec-driven multi-agent pipeline: a Main Architect splits a spec into module folders with one owner each, module agents implement them in parallel isolated worktrees under enforced write scopes, every accepted module is committed on a per-run branch, reviewers gate each stage, and rework runs close the loop.",
"author": {
"name": "Nero"
},
"license": "MIT",
"keywords": [
"multi-agent",
"workflow",
"worktree",
"spec-driven",
"code-ownership"
]
}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.
[module-pipeline on Agent Plugins Marketplace](https://pluginsmp.com/plugins/module-pipeline)