By bishwas-py
Universal dev workflow plugin — auto-detects your stack, orchestrates tasks, PRs, reviews, linting, testing, and deployment. Includes /forge:recon (autonomous security & consistency auditor with confidence letters) and /forge:compare (side-by-side system comparison).
npx claudepluginhub bishwas-py/forge --plugin forgeCompare two systems side-by-side. Analyzes UI flows, logical architecture, data handling, security posture, and technical patterns between two running apps or two codebases. Use with --mode recon to crawl both UIs, or --mode code to compare codebases. Trigger on: compare systems, compare apps, side-by-side comparison, how does X differ from Y, compare these two, diff two systems.
Universal dev workflow orchestrator. Use this skill whenever working on any software project — picking up tasks from Linear or GitHub Issues, creating branches, developing features, running linting and tests, creating PRs, handling CodeRabbit reviews, or deploying. Trigger on any mention of tasks, issues, PR workflows, code review, linting, testing, migrations, deployments, or dev workflow questions. Works on any tech stack — auto-detects languages, frameworks, and tooling.
Stack-agnostic autonomous security, consistency, and quality auditor. Crawls any running web app using Playwright, runs programmatic security and accessibility scans, cross-checks UI/API/DB values, attacks forms with wild data, and produces a Confidence Letter with a scored report that forge can consume to fix issues. Authors persistent test files in the project's native Playwright flavor (TS/JS/Python/Java/.NET) for repeatable checks (zero-token execution) and uses MCP only for exploratory discovery. Trigger on: recon, audit, security check, consistency check, confidence letter, quality audit, end-to-end check, verify the app, check everything, mutation propagation, cross-page consistency, state propagation, data flow audit.
Universal dev workflow plugin for Claude Code. Auto-detects your stack, orchestrates the full development lifecycle from task pickup to merged PR — works on any project, any language.
First, add the marketplace:
/plugin marketplace add Bishwas-py/forge
Then install the plugin:
/plugin install forge
To update to the latest version:
/plugin marketplace update
Forge handles the full dev loop:
gh pr create with description + task referenceClaude Code does not yet support formal plugin dependencies (tracking issue). Forge adapts to what you have installed — it skips phases that lack their required plugin rather than failing.
That said, you'll get the most out of Forge with these installed:
| Plugin | Used for | Install |
|---|---|---|
| linear | Task fetching, status updates, project mapping | claude plugin install linear |
| github | PR creation, CI checks, review comments | claude plugin install github |
| Plugin | Used for | Install |
|---|---|---|
| feature-dev | Structured development, code architecture | claude plugin install feature-dev |
| code-simplifier | Pre-PR code cleanup | claude plugin install code-simplifier |
| playwright | E2E visual verification | claude plugin install playwright |
| frontend-design | UI/component work | claude plugin install frontend-design |
Forge degrades gracefully:
linear? — Fall back to GitHub Issues via gh, or skip task selection entirelygithub? — Skip PR creation, just run the pre-PR gatefeature-dev? — Develop without structured codebase analysisfrontend-design? — Develop UI without design-focused guidanceplaywright? — Skip E2E visual checkscode-simplifier? — Skip automated cleanup, rely on self-review onlyThe core value — stack detection, knowledge persistence, pre-PR quality gate — works with zero plugins.
MIT
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Team-oriented workflow plugin with role agents, 27 specialist agents, ECC-inspired commands, layered rules, and hooks skeleton.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Claude Code skills for Godot 4.x game development - GDScript patterns, interactive MCP workflows, scene design, and shaders
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification