By dmedina-dev
Full-lifecycle teammate orchestration: discovery, design, planning, TDD execution, deep review, and PR — single /brainstorming command with 5 persistent named teammates.
Persistent system designer teammate for brainstorming sessions. Designs multiple implementation approaches with trade-offs, produces actionable blueprints with file maps, component designs, data flows, and build sequences. Uses opus model for deeper architectural reasoning on complex trade-off analysis. Persists across design iterations for refinement based on user feedback. <example> Context: Scout completed exploration, user answered clarifying questions assistant: "Sending architect the exploration findings and user requirements to design approaches" </example> <example> Context: User wants to refine the chosen architecture approach user: "Can you make approach B work with the existing event bus instead?" assistant: "Sending architect the refinement request with the constraint" </example>
Persistent implementation lead teammate for brainstorming sessions. Executes TDD tasks from the implementation plan one at a time: writes failing tests, implements minimal solutions, verifies, commits, and self-reviews. Maintains context across tasks — remembers patterns from previous tasks to improve consistency. <example> Context: Plan approved, worktree set up, ready to implement assistant: "Sending builder Task 1 with full description and architectural context" </example> <example> Context: Reviewer found spec compliance issues in builder's work assistant: "Sending builder the reviewer's findings to fix before re-review" </example>
Persistent PR and integration specialist teammate for brainstorming sessions. Handles the final phase: verification, branch finishing (4 options), PR creation, and automated PR review with confidence-based scoring. Coordinates the handoff from implementation to merged code. <example> Context: Deep review passed, ready for PR assistant: "Spawning closer to handle verification, PR creation, and automated review" </example> <example> Context: User wants to skip PR and just merge user: "Just merge it directly" assistant: "Sending closer the merge instruction instead of PR flow" </example>
Persistent quality gatekeeper teammate for brainstorming sessions. Operates in three modes: (1) Spec validation — checks design documents for completeness and consistency. (2) Per-task review during execution — spec compliance then code quality, with the "Do Not Trust the Report" protocol. (3) Deep review after all tasks — applies 5 specialized lenses (tests, errors, types, comments, simplification) to the full implementation. <example> Context: Builder completed a task, needs spec + quality review assistant: "Sending reviewer the task spec and builder's report for two-stage review" </example> <example> Context: All tasks complete, need deep specialized review assistant: "Switching reviewer to deep mode for 5-lens quality analysis" </example> <example> Context: Spec document needs validation before planning assistant: "Sending reviewer the spec document for completeness and consistency check" </example>
Persistent codebase explorer teammate for brainstorming sessions. Performs multi-pass analysis that accumulates understanding: similar features, architecture mapping, and integration point identification. Unlike ephemeral code-explorer agents, scout retains context across passes and reports via team coordination. <example> Context: Brainstorming session starts, codebase needs exploration user: "/brainstorming add real-time notifications" assistant: "Spawning scout to explore the codebase for notification patterns and architecture" </example> <example> Context: Scout completed first pass, needs deeper analysis assistant: "Sending scout a follow-up to trace the event system integration points" </example>
Uses power tools
Uses Bash, Write, or Edit tools
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.
Personal plugin marketplace for Claude Code. Curated collection of independent plugins — install all or pick what you need.
# Add marketplace (once per machine)
/plugin marketplace add dmedina-dev/dev-forge
# Install all working plugins at once
/plugin install forge-init
/forge-init:install-all
# Or install individually
/plugin install forge-keeper # context maintenance (recommended always-on)
/plugin install forge-superpowers # TDD, debugging, collaboration patterns
/plugin install forge-extended-dev # discovery → design → deep review → PR review
/plugin install forge-brainstorming # teammate-driven full lifecycle (requires forge-superpowers)
/plugin install forge-security # security reminder hooks
/plugin install forge-commit # commit/PR commands
/plugin install forge-hookify # custom hook rules engine
/plugin install forge-ralph # persistent loop technique
/plugin install forge-frontend-design # distinctive UI/UX design
/plugin install forge-channels-telegram # Telegram channel bridge (requires Bun)
Always-on plugins for daily development.
| Plugin | Purpose | Commands |
|---|---|---|
| forge-keeper | Context maintenance + PreCompact hook | /sync, /status, /recall, /segment-doc |
forge-keeper commands:
/sync — analyze changes, propose CLAUDE.md + rules + exemplars updates/status — context health report with drift detection/recall — search session log for past decisions/segment-doc — split monolithic .md into focused pieces for better context loading| Plugin | Purpose | Commands |
|---|---|---|
| forge-superpowers | TDD, debugging, parallel agents, code review, worktrees, plans | Skills-based (auto-triggered) |
| forge-extended-dev | 4-phase development workflow (requires forge-superpowers) | /feature-dev, /deep-review, /pr-review |
| forge-brainstorming | Teammate-driven full lifecycle with 5 persistent agents (requires forge-superpowers) | /brainstorming |
| Plugin | Purpose | Commands |
|---|---|---|
| forge-commit | Git commit and PR workflow | /commit, /commit-push-pr, /clean-gone, /release |
| forge-security | Security reminder hooks (XSS, injection, eval, etc.) | Passive — hooks on Edit/Write |
| forge-hookify | Custom hook rules engine with .local.md rules | /hookify, /hookify-list, /hookify-configure, /hookify-help |
| forge-ralph | Persistent loop: Claude keeps working across stop events | /ralph-loop, /cancel-ralph, /ralph-help |
| forge-frontend-design | Distinctive, production-grade UI/UX design | Skill-based (auto-triggered) |
| forge-ui-expert | UI/UX design intelligence: 67 styles, 96 palettes, 57 font pairings, 13 stacks | Skill-based (auto-triggered) |
| forge-profiles | Plugin profile manager — switch plugins + MCP servers per work mode | /profile-create, /profile-list, /profile-change |
| Plugin | Purpose | Commands |
|---|---|---|
| forge-channels-telegram | Telegram bridge — push messages into running session, reply from Claude | Skills: telegram:configure, telegram:access (auto-triggered) |
Install when needed, uninstall after. Don't consume context when not in use.
| Plugin | Purpose | When to install |
|---|---|---|
| forge-init | Project bootstrapper + install-all + AGENTS.md generation | New project: /forge-init:init then /forge-init:install-all then uninstall |
| forge-plugin-dev | Plugin development toolkit (7 skills, 3 agents) | Developing plugins: /create-plugin then uninstall |
| forge-context-mcp | MCP server setup guide (Context7, Serena, XRAY) | Setting up codebase intelligence: configure servers then uninstall |
claude --plugin-dir plugins/<name>docs/dependencies.mdCurated plugins retain their original authorship. No claim of original authorship is made for curated content.
Original author: Jesse Vincent (@obra)
| Plugin | Upstream | Version |
|---|---|---|
| forge-superpowers | superpowers | v5.0.6 |
npx claudepluginhub dmedina-dev/dev-forge --plugin forge-brainstormingGit workflow commands: /commit (smart commit with style-matching), /commit-push-pr (branch → commit → push → PR), /clean_gone (remove stale branches), /release (bump changed plugins, tag, push).
Exports a dev-forge marketplace into a new standalone repository. Interview-driven: select plugins, apply customizations, generate complete marketplace structure. Designed to be uninstalled after use.
Create custom hooks from natural language to prevent unwanted behaviors. Regex-based rules in .local.md files, no coding or restart required.
Security reminder hook: warns about potential security issues (command injection, XSS, eval, pickle, etc.) when editing files. Passive, low overhead.
Keeps CLAUDE.md, project docs and memories in sync after development sessions. Context-aware semantic detection plus explicit /sync command for human-driven updates. Safety-net git-based hook at relaxed thresholds.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.
Write feature specs, plan roadmaps, and synthesize user research faster. Keep stakeholders updated and stay ahead of the competitive landscape.
Curate auto-memory, promote learnings to CLAUDE.md and rules, extract proven patterns into reusable skills.