By samrom3
ADR lifecycle management for Claude Code. Create, supersede, deprecate, and validate Architecture Decision Records across multiple directories using a CLAUDE.md convention for ADR location discovery.
This skill should be used when the user asks to 'validate ADRs', 'check ADR structure', 'run adr-check', 'check for undocumented decisions', or when lifecycle skills and gate agents need to validate ADR files. Supports Global mode (all discovered ADR directories, including diff-based warnings), Scoped mode (single file, directory, or natural-language query — no diff noise), and future Diff mode.
This skill should be used when the user asks to 'create an ADR', 'document an architectural decision', 'record a design decision', 'write an architecture decision record', or when the model identifies an architectural decision in context that warrants formal documentation. Evaluates decision worthiness before authoring and guides section drafting.
This skill should be used when the user asks to 'deprecate an ADR', 'mark an ADR as obsolete', 'retire an architectural decision', 'flag an ADR as no longer applicable', or when an existing architectural decision is no longer relevant and should be marked as deprecated while preserving history.
This skill should be used when the user asks to 'supersede an ADR', 'replace an architectural decision', 'update an ADR with a new decision', 'mark an ADR as superseded', or when an existing architectural decision has changed and needs to be replaced while preserving the historical record.
A curated marketplace of custom Claude Code plugins built by @samrom3 with help from his friends and colleagues.
AI-augmented development for engineers who stay in the loop. Interviews you to build a PRD (with requirement analysis and conflict resolution), then runs an autonomous specialist agent team with back-pressure gates to implement it — while you review, guide, and approve at every milestone.
/prd, /hyperteam.Refer to the Hyperloop guide for more usage and details.
ADR lifecycle management for Claude Code. Create, supersede, deprecate, and validate Architecture
Decision Records across single or multiple directories using a CLAUDE.md convention for discovery.
Integrates with hyperloop's gate for automated ADR validation.
/adr-create, /adr-supersede, /adr-deprecate, /adr-checkRefer to the adr-wizard guide for more usage and details.
/plugin marketplace add samrom3/claude-hyper-plugs
/plugin install hyperloop@hyper-plugs
See the Claude Code plugin marketplaces documentation for details.
.claude-plugin/plugin.json with metadata:
{
"name": "your-plugin",
"version": "1.0.0",
"description": "What your plugin does.",
"author": {
"name": "Your Name",
"url": "https://github.com/you"
},
"license": "MIT"
}
agents/ and/or skills/ with Markdown definitionsREADME.md documenting usageMIT
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub samrom3/claude-hyper-plugs --plugin adr-wizardAI-augmented development for engineers who stay in the loop. Interviews you to build a PRD (with requirement analysis and conflict resolution), then runs an autonomous specialist agent team with back-pressure gates to implement it — while you review, guide, and approve at every milestone.
Architecture Decision Records authoring and management
Human-in-the-loop Architecture Decision Record workflow
ADRs Management plugins for Architecture Decision Records analysis, generation, and linking
Interactive skill that analyzes a task, proposes an agent team composition, and creates the team after user confirmation
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Make your AI agent code with your project's architecture, rules, and decisions.