Citadel plugin for Grok Build

Name: Citadel
Author: SethGammon

Community Claude Code plugin, installs in GrokPluginAutomation

The operating layer for Claude Code + OpenAI Codex: persistent project memory, intent routing, safety hooks, cost telemetry, and parallel agent fleets.

How to install Citadel in Grok Build

grok plugin install SethGammon/Citadel --trust

✓ Install-checked in Grok Buildchecked Oct 18, 2026

Review before you trust it. --trust lets this plugin's hooks, MCP servers and scripts run code on your computer. It's a community repo that neither xAI nor GrokStacks has reviewed, so read its code first.

We install this repo directly: Grok Build 1.0.62 can't install it through its own marketplace file. Then start a new Grok session, or press r in /plugins, to load it.

Command format: Grok Build's plugin guide

Runs a local MCP server (with npx, uvx or similar), so that tool needs to be installed, for example Node.js for npx.

What we checked: on Oct 18, 2026 it installed with grok 1.0.62 and Grok found 48 skills, 1 subagent. That's an install check only: we haven't run it in a live Grok session.

What it contains

Skills (25)

architect — Given a PRD, produces an implementation architecture: file tree, component breakdown, data model, and a phased build plan with end conditions that Archon can execute directly. Multi-candidate evaluation for key decisions.
archon — Autonomous multi-session campaign agent. Decomposes large work into phases, delegates to sub-agents, reviews output, and maintains campaign state across context windows. Use for work that spans multiple sessions and needs persistent state,
ascii-diagram — Generate perfectly aligned ASCII diagrams — architecture, flow, sequence, box-and-arrow. Uses a programmatic character-grid approach so alignment is guaranteed by math, not token prediction. Includes post-render verification.
autopilot — Intake-to-delivery pipeline. Processes pending items from .planning/intake/: briefs new ideas, executes approved work through research → plan → build → verify. Drop a file in .planning/intake/ and invoke this skill.
cost — Deep cost exploration and transparency. Shows real token usage, session costs, campaign spend, burn rates, and model breakdown. Reads Claude Code's native session data for exact numbers. Complements /dashboard with focused cost views.
create-app — End-to-end app creation from a single description. Five tiers: blank project, guided, templated, fully generated, or feature addition to existing codebase. Routes through PRD, architecture, and Archon campaign with verification at every ste
create-skill — Creates new skills from the user's repeating patterns. Interview-driven: discovers the task, analyzes failure modes, generates a production SKILL.md, installs it, tests it on a real target, and teaches the user how to use it. Use when a use
daemon — Continuous autonomous operation mode. Keeps campaigns running 24/7 by chaining Claude Code sessions via RemoteTrigger. Each session picks up from the campaign's continuation state, works until context runs low or the phase completes, then s
dashboard — Real-time harness observability dashboard. Reads campaigns, fleet sessions, telemetry, and pending queues to present a snapshot of harness state at a glance. Invoked by /dashboard, /do status, or phrases like "what's happening" and "show ac
decision-map — Turn a loose idea into a git-tracked, session-resumable map of typed investigation tickets, then drive them to resolution one at a time. The planning-loop engine for work that is still being figured out — too fuzzy for a campaign, too big f
deploy-steward — Mainline deploy steward. Consumes ready PRs, owns a lease on mainline landing, refreshes PR state, updates stale branches, waits for CI and deploy gates, merges or queues one candidate at a time, and opens repair tasks for failures.
design — Generates and maintains a design manifest for visual consistency. In existing projects, reads current styles and documents the design language. In new projects, asks a few questions and generates a starter manifest. The post-edit hook reads
do — Unified router that auto-routes user intent to the right direct action, skill, orchestrator, or explicit Operation Control plan. Classifies input by scope, complexity, persistence needs, and parallelism, then dispatches to the cheapest path
doc-gen — Documentation generator with three modes: function-level (JSDoc/docstrings), module-level (directory READMEs), and API reference (endpoints/exports). Reads existing project doc style and matches it. Never generates docs that just restate wh
evolve — Research-driven multi-cycle improvement director. Forms causal hypotheses about why scores are low, validates them with scout agents before attacking, dispatches axis-parallel fleet attacks, extracts transferable patterns, and runs indefini
experiment — Automated optimization loop with scalar fitness function. Proposes changes in isolated worktrees, measures against a fixed baseline, and retains verified candidates locally. Supports convergence detection and diminishing returns.
fleet — Parallel campaign orchestrator. Runs multiple campaigns in coordinated waves within a single session. Spawns 2-3 agents per wave in isolated worktrees, collects discoveries, shares context between waves. Use when work decomposes into 3+ ind
grill — Relentless one-question-at-a-time interview that sharpens a vague plan or design into shared understanding before any build. The elicitation engine other planning skills call instead of inventing their own interview. Auto-trigger when the u
houseclean — Cross-drive storage audit and cleanup. Surveys all drives, finds orphaned git worktrees, large AI tool caches (.ollama, .gemini, .cursor, npm, pip), and buildable artifacts (node_modules, .venv). Produces a prioritized action plan with spec
improve — Autonomous quality improvement loop. Scores a target against a rubric, selects the highest-leverage axis, attacks it, verifies, documents, and loops. No pre-planning between iterations — each loop re-scores from scratch.
infra-audit — Reads docker-compose, env files, ORM configs, and connection strings to map current infrastructure. Flags missing layers (cache, queue, analytics) based on observed access patterns. Outputs a structured infrastructure manifest.
learn — Knowledge compiler. Extracts patterns, decisions, and anti-patterns from completed campaigns and evolve cycles, then compiles them into structured wiki pages that integrate with existing knowledge rather than appending isolated files. Imple
live-preview — Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
loop — Bounded foreground repetition for the current session. Creates a loop contract, runs or coordinates an action plus verifier up to a declared attempt limit, and records evidence under .planning/loops/. Use for repeat-until-pass work that is
map — Structural codebase index generator. Builds a compact JSON map of files, exports, imports, dependency graph, and roles. Queryable by keyword. Injected into fleet agents as context slices to reduce token usage on code navigation.

Subagents (7)

citadel:arbiter — Strong-tier, different-family, adversarial, ACTING judge with FINAL veto on holistic acceptance. Unlike the lightweight phase-validator (which reads a HANDOFF and checks exit-condition prose), the arb
citadel:arch-reviewer — Read-only architecture reviewer. Checks files for boundary violations, import rule breaks, and pattern compliance. Does not modify files.
citadel:archon — Autonomous vision agent. Decomposes vague or specific direction into campaign phases. Delegates to Marshals and specialists. Reviews output against quality standards. Maintains campaign state across i
citadel:fleet — Parallel campaign orchestrator. Runs multiple campaigns in coordinated waves within a single session. Spawns 2-3 agents per wave, collects discoveries, shares context between waves, rebalances priorit
citadel:knowledge-extractor — Extracts reusable patterns, pitfalls, and decisions from completed work and writes them to the wiki staging area. Run after finishing a body of work to capture what was learned. Call /learn --compile
citadel:phase-validator — Lightweight handoff validator. Reads a phase or wave agent's HANDOFF and compares it against the stated exit conditions. Returns a structured verdict (pass/fail) with specific reasons. Never modifies
citadel:policy-enforcer — Blocking policy judge. Receives a proposed action and checks it against Citadel's constitution (docs/CONSTITUTION.md). Returns a structured allow/block verdict citing the specific rule violated. Never

MCP servers (2)

citadel-state — stdio server
codebase-memory — stdio server

About this listing

Citadel is a community plugin on GitHub by SethGammon, written as a Claude Code plugin that Grok Build installs. We install-checked it in Grok; we haven't run it in a live session or reviewed its code. When we installed it, Grok found 25 skills, 7 subagents, 2 MCP servers. Its license is MIT. We checked commit 1dc5e9627d70. It's one of 82 listings in the Automation category on GrokStacks.

Citadel FAQ

How do I install Citadel in Grok Build?

Run grok plugin install SethGammon/Citadel --trust. We install-checked this command in Grok Build. We install this repo directly: Grok Build 1.0.62 can't install it through its own marketplace file. Then start a new Grok session, or press r in /plugins, to load it.

Is Citadel an official Grok Build plugin?

No. Citadel is a community plugin on GitHub by SethGammon, not in xAI's official Grok Build marketplace. We checked that it installs and what Grok loads from it, but haven't run it in a live Grok session or reviewed its code.

What does Citadel include?

According to what Grok loaded in our install check, Citadel includes 25 skills, 7 subagents, 2 MCP servers: architect, archon, ascii-diagram, autopilot, cost, create-app….

Details

Type: Plugin
Category: Automation
Source: Community Claude Code plugin, installs in Grok
License: MIT
Author: SethGammon
Version: 1.4.4
Keywords: agent-orchestration, agent-workflow, ai-agents, claude-code-plugin, claude-plugins, codex-plugin, developer-tools, mcp
Source repo: https://github.com/SethGammon/Citadel
Checked commit: 1dc5e9627d70
Homepage: https://sethgammon.github.io/Citadel/
Checked by GrokStacks: Install-checked in Grok Build on Oct 18, 2026; not run in a live session

Something wrong or missing? Submit or improve this listing. Marketplace listings also refresh automatically every night.

For maintainers: badge and embeds

Maintain Citadel? Add the badge; it links to this page.

Markdown

[![Listed on GrokStacks](https://grokstacks.com/badge.svg)](https://grokstacks.com/p/citadel/)

HTML

<a href="https://grokstacks.com/p/citadel/"><img src="https://grokstacks.com/badge.svg" alt="Listed on GrokStacks" width="164" height="28"></a>

Embed card (static HTML and inline CSS, no JavaScript). Preview:

CitadelCommunity plugin for Grok Build · 25 skills, 7 subagents, 2 MCP serversThe operating layer for Claude Code + OpenAI Codex: persistent project memory, intent routing, safety hooks, cost…View on GrokStacks →

<a href="https://grokstacks.com/p/citadel/" style="display:block;max-width:380px;box-sizing:border-box;padding:14px 16px;border:1px solid #2a2e3c;border-radius:12px;background:#0a0b0f;color:#e8eaf0;font:14px/1.45 -apple-system,Segoe UI,Roboto,Helvetica,Arial,sans-serif;text-decoration:none"><span style="display:block;font-size:16px;font-weight:700;color:#e8eaf0">Citadel</span><span style="display:block;margin:2px 0 8px;font-size:12px;color:#9aa0b1">Community plugin for Grok Build · 25 skills, 7 subagents, 2 MCP servers</span><span style="display:block;margin:0 0 10px;color:#c9cdd8">The operating layer for Claude Code + OpenAI Codex: persistent project memory, intent routing, safety hooks, cost…</span><span style="font-size:12px;font-weight:600;color:#7c9cff">View on GrokStacks →</span></a>

Markdown summary

**[Citadel on GrokStacks](https://grokstacks.com/p/citadel/)**: Community plugin for Grok Build with 25 skills, 7 subagents, 2 MCP servers. Install: `grok plugin install SethGammon/Citadel --trust`

More on badges, embeds and keeping your listing up to date: GrokStacks for plugin authors.

Also in Automation

Agent Sop

Natural language workflows that enable AI agents to perform complex, multi-step tasks with consistency and reliability.

Community Claude Code plugin, installs in GrokPluginAutomation

Agentic Creator Os

Agentic Creator OS (ACOS), by GenCreator: reusable orchestration, skills, commands, agents and local safety tooling for creator workflows.

Community plugin, built for Grok BuildPluginAutomation

Agentlas OS

Agent OS: keep specialist agents in a hub, spin up a temporary orchestrator per task. Local-first, works with any model.

Community Claude Code plugin, installs in GrokPluginAutomationMCP: manual setup

Agentrq

AgentRQ: Human-in-loop realtime conversational task manager for AI Agents. Self-hosted! Control your own agents from wherever you want Mobile, Web, Desktop. Designed to work well with your own Claude subscriptions and any harness with ACP support.

Community Claude Code plugin, installs in GrokPluginAutomationNeeds sign-in