Agent
The Integration agent specializes in the fragile boundary between your application and the outside world. External APIs fail, webhooks arrive with forged signatures, OAuth tokens expire mid-session, and rate limits get hit at the worst possible time. The Integration agent writes the code that handles all of this…
Agent
The Learning agent is NXTG-Forge's institutional memory. It observes how you work -- which agents you invoke, what corrections you make, what coding patterns you prefer -- and encodes those observations into persistent preferences that improve every future session.
Agent
The Master Architect is the senior engineer who has seen systems fail and succeed at scale. It reviews, challenges, and shapes every system design decision through a lens of radical simplicity: if a junior developer cannot understand it in 10 minutes, it is too complex. Complexity is not sophistication -- it is…
Agent
The Oracle is NXTG-Forge's proactive governance sentinel. While the Builder focuses on implementation and the Guardian enforces quality gates, the Oracle answers three questions continuously: Are we building what we said we would build? Is the implementation diverging from the stated direction? Does this change…
Agent
The Orchestrator is the conductor of the entire NXTG-Forge experience. It is the first agent you interact with and the one that decides which specialist agents handle which problems. When you activate Forge, the Orchestrator presents a canonical 4-option menu -- Continue/Resume, Review & Plan Features, Soundboard…
Agent
The Performance agent measures first and optimizes second. When your dashboard takes forever to load or your bundle exceeds 2MB, it does not guess at the cause -- it profiles, identifies the specific bottleneck, and applies targeted fixes. It understands the full performance stack: JavaScript bundle size and…
Agent
The Planner is the strategic architect you wish you had on every project. When you say "I need OAuth" or "we should add real-time notifications," it does not jump to code. Instead, it runs a five-phase planning framework: requirements gathering, architecture design, task breakdown, risk analysis, and implementation…
Agent
The Product Strategist bridges vision and execution. It takes unvalidated product ideas and runs them through rigorous frameworks -- Jobs-to-be-Done analysis, RICE/MoSCoW prioritization, competitive positioning, Lean Canvas, Wardley Mapping, and pricing models -- to produce documents that teams can execute against…
Agent
The QA Sentinel designs test strategy -- what kinds of tests, where, why, and how they compose into a quality system that actually catches bugs. It does not write tests (that is the Testing agent). It does not forensically audit existing tests (that is the CRUCIBLE Detective). It is the architect of quality -- the…
Agent
The Refactor agent improves code structure while preserving external behavior. It takes an 800-line file and splits it into focused modules. It finds duplicated WebSocket logic across four components and extracts a reusable hook. It takes a function with cyclomatic complexity of 15 and simplifies it with early returns…
Agent
The Release Sentinel is a documentation management specialist that maintains synchronization between your code and your docs. It knows that stale documentation erodes trust faster than missing documentation -- a wrong answer is worse than no answer.
Agent
The Revenue Architect is the bridge between product vision and sustainable revenue. Every feature decision has a revenue implication -- this agent makes those implications explicit. It thinks in terms of value capture, not just value creation, and it designs pricing models that align price with value delivered rather…
Agent
The Scout produces actionable intelligence that drives decisions, not slide decks that gather dust. It tracks competitors, maps ecosystems, sizes markets, and identifies strategic whitespace -- but every analysis ends with a specific decision recommendation, a confidence level, and an expiration date.
Agent
The Security agent is a focused penetration tester for your codebase. While the Guardian runs security as one dimension of its broad quality gate, the Security agent goes deep -- it checks all ten OWASP categories, audits authentication and authorization implementations, validates CSP and CORS configurations, scans…
Agent
The Testing agent writes tests so you do not have to start from scratch. Hand it a new service class, React component, or utility function, and it generates tests covering happy paths, error cases, and edge cases with properly shaped mocks. It detects your testing framework (Vitest, Jest, pytest) and generates tests…
Agent
The UI agent is a frontend specialist that builds production-quality React components. It does not just generate JSX -- it creates components that are typed with interfaces, styled with Tailwind (never inline styles, never CSS modules), accessible with ARIA attributes and keyboard navigation, testable with data-testid…
Agent
The Wordsmith writes text that makes people do things: install, click, buy, read further, trust. Every sentence earns its place or gets cut. It writes like a senior engineer explaining something to a peer over coffee -- direct, opinionated, concrete, human, and honest.
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…