By cjy5507
Structure, ownership, and continuable state for long-running coding agent work.
npx claudepluginhub cjy5507/forge --plugin forgeForge Analyst — deep codebase analysis via codebase-memory-mcp for architecture mapping, impact analysis, dependency tracing, and quality assessment
Forge Bug Tracker — manages .forge/holes/ directory, tracks issue lifecycle, provides status summaries
Forge CEO — project intake, scope decisions, blocker resolution, delivery sign-off
Forge CTO — architecture design, technical feasibility, interface contracts, code rules, scale-appropriate decisions
Forge Design Team — meta-agent definition for CTO + Designer peer collaboration via Team pattern during design phase
Forge Designer — wireframes, design systems, component specs, design tokens, visual consistency
Forge Developer — implements assigned modules in isolated worktrees, follows code-rules.md, asks fact-checker when unsure
Forge Fact Checker — verifies technical claims before code is written, returns evidence or blocks
Forge Lead Developer — task splitting, lane-graph management, worktree orchestration, code review, PR integration, consistency enforcement
Forge PM — client interview, requirements elicitation, spec generation with zero ambiguity
Forge Publisher — converts design specs to pixel-perfect markup, responsive layouts, CSS, a11y
Forge QA Engineer — functional, visual, contract, regression, and edge-case testing against spec and design
Use this reference when writing architecture, contracts, or code rules.
Use this reference when generating delivery documentation.
Use this reference when planning or executing QA passes.
Use this reference when a Forge issue needs structured diagnosis.
Use this reference when running Forge security review.
Forge Researcher — investigates external options, gathers evidence, compares approaches, and prepares decision-ready research briefs
Forge Security Reviewer — OWASP Top 10 audit, secrets scanning, auth/authz review, dependency vulnerability check
Forge Technical Writer — generates README, API docs, component docs, and deployment guides at delivery
Forge Troubleshooter — deep problem diagnosis for complex, cross-module, and hard-to-reproduce issues
Run codebase analysis via Analyst agent. Triggers: "forge analyze", "analyze codebase", "code analysis", "architecture analysis", "impact analysis", "dependency trace", and first-principles redesign requests that need an assumption audit plus execution plan.
Use when canceling or cleaning up an active Forge project. Removes worktrees, clears state, preserves code already merged to main.
Continue an existing Forge project after a pause, restart, or interruption. Triggers: "forge continue", "pick up where we left off", "resume".
Use when Forge delivers the completed product. Tech writer generates docs, CEO compiles delivery report with spec coverage and known issues.
Use when Forge reaches the design phase or the user asks for technical architecture, UI spec, contracts, or code rules before implementation. Trigger on requests for architecture design, component specification, design tokens, interface contracts, or phased pre-build planning.
Use when Forge starts implementation after design approval, or when the user asks for parallel module development with worktrees, scoped tasks, PR review, and living-standard enforcement. Trigger on requests to split implementation, dispatch developers, or enforce consistent multi-agent coding.
Use when Forge begins requirements gathering. PM interviews the client one question at a time until all ambiguity is eliminated and a complete spec is produced.
Collapsed Forge pipeline for medium-complexity tasks. Use when the user says "forge express", "quick build", or when a task is too complex for a single prompt but doesn't warrant the full 8-phase pipeline.
Use when Forge enters the bug fix loop. Routes simple issues to developers, complex issues to troubleshooter for root cause analysis.
MANDATORY Forge entry point. Use when the user explicitly says "forge", "build a harness", "set up Forge", asks Forge to build a new product, or asks Forge to diagnose/fix/analyze an existing project. If the request is for a phased team workflow, build-vs-repair routing, or harness-based execution, you must start here.
Show Forge project state and harness metrics. Triggers: "forge info", "where are we?", "show progress", "forge metrics", "measure Forge".
Use when Forge receives a new project request. CEO evaluates feasibility, scope, and information completeness before starting discovery.
Use when Forge reaches the planning phase between design and development. Lead Dev turns approved design artifacts into an execution plan, lane graph, and task briefs using Forge's native decomposition helpers.
Use when Forge begins quality assurance. QA engineer runs functional, visual, contract, regression, and edge-case tests against the spec.
<Purpose>
Use when the user wants to undo Forge progress and return to an earlier checkpoint or phase. Triggers include "rollback", "go back", "the earlier version was better", "go back to design", and any request to restore a previous Forge tag safely.
Use when Forge performs security review. Security reviewer audits OWASP Top 10, scans for secrets, reviews auth/authz logic.
Skip to a specific Forge phase. Use when the user says "forge skip", "skip to develop", "skip phase", or wants to bypass non-essential phases for their current task.
View or change the current Forge tier level. Use when user says "forge tier", "show tier", "change tier", "set tier to light/medium/full", or wants to understand or control the guardrail level.
Use when Forge needs deep bug diagnosis instead of a quick patch. Trigger on intermittent bugs, unclear root cause, multi-module breakage, repeated failed fixes, or requests like "analyze this", "root cause", "why is this failing?", and "investigate this regression". This skill must be used before broad changes on complex failures.
Battle-tested Claude Code plugin for engineering teams — 48 agents, 184 skills, 79 legacy command shims, production-ready hooks, and selective install workflows evolved through continuous real-world use
Matches all tools
Hooks run on every tool call, not just specific ones
Modifies files
Hook triggers on file write and edit operations
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, rules, and legacy command shims evolved over 10+ months of intensive daily use
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Complete developer toolkit for Claude Code
External network access
Connects to servers outside your machine
External network access
Connects to servers outside your machine
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools