Agent Plugins Marketplace
← All plugins

ai-software-delivery-room

v3.2.1

Multi-agent software delivery for Claude: discovery (brief, roadmap, business case, use cases), architecture, sprint execution with a plan→build→independent-QA triad, product-integrity traceability with drift detection and cross-sprint regression, live Cypress E2E, git workflow, and context discipline (measured facts, contract pre-flight, budgeted context packs). The state machine lives in scripts, not the model's memory.

Claude Code6 Skills

By Bilal Khan0 GitHub starsUpdated 1 hour ago

Directory evidence

Runtimes
Claude Code
Parsed components
6 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 ai-software-delivery-room 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 ai-software-delivery-room@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/Mbialuddinkhan/ai-software-delivery-room

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

ai-software-delivery-room/
├── .claude-plugin/plugin.json
├── skills/architect/SKILL.md
├── skills/asdr/SKILL.md
├── skills/discover/SKILL.md
├── skills/longhorizon/SKILL.md
├── skills/release/SKILL.md
└── skills/riskgate/SKILL.md

Included Skills6

architectskills/architect/SKILL.md

Use this skill when the user wants to design the technical architecture for a software project — system design, database model, API design, security architecture, and DevOps plan. Requires discovery docs to already exist. Trigger phrases: "architect", "design the architecture", "system design", "technical blueprint", "design the system", "create architecture docs".

asdrskills/asdr/SKILL.md

Use this skill when the user wants to build software from scratch, run the full AI Software Delivery Room workflow, turn a rough idea into production-grade software, create an app, SaaS, dashboard, API, MVP, or automation product, or set up a complete multi-agent SDLC. Trigger phrases: "build me", "I want to create", "let's build", "full ASDR", "start a new software project", "run the delivery room".

discoverskills/discover/SKILL.md

Use this skill when the user wants to run the discovery and planning phase for a software idea — product brief, requirements, user stories, and acceptance criteria — before moving to architecture or coding. Trigger phrases: "discover", "product discovery", "define requirements", "write a product brief", "plan my software", "what should I build", "let's scope this out".

longhorizonskills/longhorizon/SKILL.md

Use this skill when the user wants to run only the long-horizon Planner → Generator → Evaluator coding harness without the full strategic discovery phase. Best for when architecture docs already exist or the user wants to jump straight to building. Trigger phrases: "long horizon", "start coding", "run the harness", "planner generator evaluator", "build with sprints", "just start building".

releaseskills/release/SKILL.md

Use this skill when the user wants to package and prepare the final release — changelog, release notes, deployment checklist, and post-release monitoring plan. Requires riskgate to have passed first. Trigger phrases: "release", "package the release", "prepare release", "release notes", "create changelog", "final release".

riskgateskills/riskgate/SKILL.md

Use this skill when the user wants to run the final risk gate before releasing software — checking security, tests, deployment readiness, and classifying the release. Must be run before the release skill. Trigger phrases: "risk gate", "riskgate", "classify my release", "is this ready to ship", "final review", "pre-release check", "run risk assessment".

Plugin manifests1

.claude-plugin/plugin.json
{
  "name": "ai-software-delivery-room",
  "version": "3.2.1",
  "description": "Multi-agent software delivery for Claude: discovery (brief, roadmap, business case, use cases), architecture, sprint execution with a plan→build→independent-QA triad, product-integrity traceability with drift detection and cross-sprint regression, live Cypress E2E, git workflow, and context discipline (measured facts, contract pre-flight, budgeted context packs). The state machine lives in scripts, not the model's memory.",
  "author": {
    "name": "Bilal Khan",
    "email": "[email protected]"
  },
  "homepage": "https://github.com/Mbialuddinkhan/ai-software-delivery-room",
  "keywords": [
    "sdlc",
    "multi-agent",
    "software-delivery",
    "long-horizon",
    "harness",
    "sprints",
    "qa"
  ]
}

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.

[ai-software-delivery-room on Agent Plugins Marketplace](https://pluginsmp.com/plugins/ai-software-delivery-room)