Opinionated development workflows for Go + React/TypeScript projects — BDD, TDD, CI/CD, quality gates
Orchestrate the full feature development cycle — from rough prompt through BDD scenarios, TDD implementation, to quality verification. Use when adding any new feature, capability, or behavior. This is the primary development workflow enforced by CLAUDE.md. Trigger on any feature request, behavior description, or when the user says "add", "implement", "build", "create" followed by a feature description. Even for "simple" features, use this workflow.
Transform a rough feature prompt into expert Gherkin scenarios and generate step definition stubs. Use when starting any new feature, adding behavior, or when the user provides a feature description (even vague ones). Trigger on phrases like "add feature", "I want users to be able to", "new capability", "implement X", or any description of desired behavior. This skill acts as a BDD analyst — it proposes concrete scenarios rather than asking clarifying questions.
Scaffold a complete Go + React/TypeScript project. Gathers project info interactively, then runs the forge CLI to generate all files deterministically. Trigger on "new project", "bootstrap project", "scaffold project", "create project", or "init project".
Drive test-driven development with strict red/green/refactor discipline. Use when implementing any feature, fixing bugs, or writing new code. Trigger on phrases like "implement this", "write the code", "build this feature", "fix this bug", or when transitioning from BDD scenarios to implementation. This skill enforces that failing tests exist before implementation code is written.
A Claude Code plugin for bootstrapping and developing Go + React/TypeScript projects with BDD and TDD discipline.
Add the marketplace and install the plugin from within Claude Code:
/plugin marketplace add petrepopescu21/forge
/plugin install forge
| Command | Description |
|---|---|
/bootstrap | Scaffold a complete project — collects inputs, runs the forge CLI, installs deps, verifies quality gates |
/feature | Full feature cycle: prompt → BDD scenarios → TDD implementation → quality verification |
| Skill | Type | Purpose |
|---|---|---|
forge:bootstrap-project | orchestrator | Gathers inputs, runs forge CLI to scaffold projects in ~50ms |
forge:add-feature | orchestrator | BDD → TDD → quality gates |
forge:bdd-feature | workflow | Turns prompts into Gherkin scenarios with step stubs |
forge:tdd-cycle | workflow | Red/green/refactor discipline |
Forge has two parts:
cmd/forge/) — a deterministic Go binary that generates project files from embedded templates across 11 layers (go-module, react, makefile, linting, bdd, playwright, ci, sonar, helm, claude-md, and common)/bootstrap scaffolds a complete project with all layers/feature drives BDD → TDD → quality for each featuremake lint && make typecheck && make test) run automaticallyThe generated CLAUDE.md ensures all future Claude Code sessions automatically use these skills.
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 petrepopescu21/forge --plugin forgeScaffold new projects and add features with best-practice templates
React/TypeScript frontend + Go backend enforcement harness. 92 wired hooks across 101 scripts enforce patterns on every edit. Green != done: `test-warning-check` surfaces warnings on passing test/lint/type runs (DeprecationWarning, React `act()`, unhandled rejection, `@ts-ignore`); `ci-warning-audit` Stop-hook scans `gh run view --log` on green CI for deprecations / console warnings / skipped tests. 66 skills from TDD through CI-green PR, including /steelman anti-sycophancy guard + /snyk-ux-security per-path vuln sweep (JS + Go ecosystems; exploitability-triage first gate via `bun why`/`go mod why`/`govulncheck`; top-level direct dep bump first, parent dep bump second, resolutions/overrides/replace as last resort only with follow-up TODO to remove; React 18 pin + changelog-walked major bumps + no-deferral escalation; Go `snyk test --file=go.mod` + `go get -u` + `go mod tidy` + `govulncheck` verify). Session exit blocked while PR review threads remain unresolved. TypeScript escape hatches blocked at Edit. tsconfig strictness weakening blocked. Worktree isolation + branch safety hook-enforced. bun.lock + yarn.lock parity enforced (Snyk IO doesn't parse bun.lock). 21 LLM failure modes enforced: 7 Karpathy single-agent + 14 MAST multi-agent (Cemri et al. NeurIPS 2025). OWASP + STRIDE subset + snyk/bun audit. Core Web Vitals perf gate. MCP ban with CLI redirect (~20x token savings). Agent-browser wrap (~91% token reduction for AI browsing). 3-hat plan review (product/engineering/design). 9 agents (adds plan hats + karpathy reference), 5 routines. Opus 4.7 tuned, POSIX-friendly.
Full-cycle project development - brainstorm ideas, create specifications, plan architecture, initialize projects, and execute implementation with integrated workflows from superpowers and spec-kit
DDD-driven development skills, sub-agents and workflow commands for Rust + React projects
Opinionated engineering agent team with progressive-disclosure specs for Python / TypeScript / Go monorepos. Ships PM / SWE / Tester / On-Call sub-agents, /day and /night pipelines, and a library of language/framework/infra specs that agents load on-demand.
LLM OS for software engineering. 10 agents, 5-phase TDD workflow, 45 rules (3-tier), 43 skills, 89 commands, 26 hooks, 6 MCP servers. Memory-as-hint architecture, 3-tier context compression, multi-agent orchestration.