Forge Plugin: Zero-dependency governance for Claude Code. 21 commands, 22 agents, 29 skills.
Command
/forge:agent-assign is the intelligent dispatcher for Forge's 22 specialized agents. You describe a task, and the command analyzes its domain (architecture, backend, frontend, testing, devops, security, docs), complexity, and required skills, then recommends the best-fit agent with a match score and reasoning. It also…
Command
/forge:ceo-loop-cancel is the graceful exit from an active CEO-LOOP ORBIT cycle. It reads the current loop state, collects session statistics (iterations completed, decisions made, auto-approved count, escalated count, accuracy percentage, trust level), writes a final session summary to the progress file, sets the…
Command
/forge:ceo-loop starts an autonomous decision-making engine that runs in a continuous ORBIT cycle: OBSERVE pending decisions and project state, REASON about each decision using precedent from the decision journal, BUILD the actual decisions (approve, modify, escalate), INSPECT via retrograde analysis of previous…
Command
/forge:checkpoint creates lightweight project state snapshots that capture your git commit, branch, uncommitted changes, governance state, and environment metadata in a single JSON file. Unlike git stash or branches, checkpoints are Forge-aware -- they save governance state alongside git state so you can restore not…
Command
/forge:command-center is the command you run when you sit down and ask "what should I work on?" It presents a four-option menu -- Continue/Resume, Review & Plan Features, Soundboard, and Health Check -- each backed by real data from both local state and the forge-orchestrator. Before showing the menu, it runs a…
Command
/forge:compliance audits every dependency in your project against your project's license (typically MIT). It scans the full dependency tree via npm ls, reads each package's license field, and classifies every dependency as Compatible (MIT, ISC, BSD, Apache-2.0), Conditional (LGPL, MPL), Incompatible (GPL, AGPL, SSPL)…
Command
/forge:dashboard generates and opens a visual HTML dashboard in your browser. The dashboard is created by the governance MCP server's forgeopendashboard tool, which reads live project data (health scores, governance state, git status, code metrics) at generation time and produces a self-contained HTML file with…
Command
/forge:deploy is the safety-first deployment command. Before any deployment action occurs, it runs a five-point pre-flight validation: TypeScript compilation, full test suite, security audit, git cleanliness check, and production build. Each check produces a PASS or FAIL result, and the overall verdict is READY or NOT…
Command
/forge:docs-audit is the deep documentation quality assessment. It runs five audit dimensions: coverage analysis (what percentage of exported symbols have JSDoc), file inventory (which key files like README, CHANGELOG, CONTRIBUTING, and LICENSE exist), link validation (do internal markdown links point to real files)…
Command
/forge:docs-status answers the question "how is our documentation?" in under a minute. It checks for essential files (README.md, CHANGELOG.md, CONTRIBUTING.md, LICENSE), counts files in the docs directory, measures JSDoc coverage on exported symbols in source code, and compares documentation freshness against source…
Command
/forge:docs-update is the documentation fixer. It compares recently changed source files (from the last 20 commits or 7 days) against documentation files to find staleness, then reads both the outdated doc and the current source code to identify discrepancies -- new functions, changed interfaces, removed features. For…
Command
Command "feature" from nxtg-ai/forge-plugin, covering /forge:feature, the pipeline, what it does, syntax & options and when to use it.
Command
/forge:gap-analysis is the deepest diagnostic command in Forge. It spawns five parallel agents (testing, docs, security, detective, performance) that simultaneously analyze your project across every quality dimension. The testing agent maps source files to test files and calculates file-level coverage. The docs agent…
Command
/forge:init is the starting point for every NXTG-Forge project. It runs a guided setup wizard that detects your project type (Node.js, Rust, Python, Go, Java), checks for existing configuration, captures your product vision and goals, then creates the governance files that power every other Forge command.
Command
/forge:integrate is the integration assistant for connecting your project to external services. It covers version control (GitHub, GitLab), monitoring (Sentry, Datadog), communication (Slack, Discord), databases (PostgreSQL, Redis, MongoDB), and cloud platforms (AWS, GCP, Vercel, Netlify). For each service, it checks…
Command
/forge:optimize is the codebase health scanner. It examines seven dimensions of code quality: large files that need refactoring (over 300 lines), type safety issues (as any and as unknown casts), dead code (exported symbols never imported elsewhere), dependency health (outdated, unused, and vulnerable packages), code…
Command
/forge:report builds an activity report from real project data. It pulls commits from git history, calculates lines changed, identifies the most-modified files, checks for open pull requests on the current branch, counts test files, reads governance sentinel log entries, and lists saved checkpoints. The result is a…
Command
/forge:restore is the dedicated restoration command -- a focused shortcut for /forge:checkpoint restore. When you provide a checkpoint ID, it reads the saved state, displays a side-by-side comparison of the checkpoint state versus your current state (branch, commit, uncommitted changes), and offers to restore the…
Command
/forge:spec is the planning-only counterpart to /forge:feature. It analyzes your existing codebase -- directory structure, code patterns, test conventions, and available dependencies -- then produces a structured specification document covering requirements (functional and non-functional), architecture (components…
Command
/forge:status-enhanced is the heavyweight sibling of /forge:status. While the standard status command gives you a quick overview, the enhanced version runs a full seven-source analysis: complete git history with a 7-day commit activity heatmap, full test suite execution with verbose output, TypeScript compilation…
Command
/forge:status is the zero-context-friendly command you run at the start of every session. It gathers data from eight sources in parallel -- project metadata, git history, test results, governance state, orchestrator task board, build output, agent/command/hook inventory, and health scores -- then renders a richly…
Command
/forge:test runs your test suite and transforms raw test output into a structured, actionable report. It starts with a pre-flight check to verify your test infrastructure is available, then constructs the appropriate test command based on your arguments, executes it, and parses the results into a summary showing…
Command
/forge:update handles the full plugin update lifecycle, including a workaround for a known Claude Code issue (#29071) where plugin update fetches new content but never merges it into the local marketplace clone. The command first detects your current installation (plugin name, scope, marketplace version), then…