Plugin Claude Code
Local Citadel plugin marketplace.
Plugin Claude Code
Local Citadel plugin marketplace.
Plugin Claude Code
Claude Code harness for routing requests, preserving run state, enforcing hooks, and recording evidence.
MCP server Claude CodeCodexCursor +2
MCP server "citadel-state" as configured in SethGammon/Citadel. Runs mcp-servers/citadel-state/index.js with node. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
MCP server "codebase-memory" as configured in SethGammon/Citadel. Runs mcp-servers/codebase-memory/index.js with node. Needs 1 environment variable to run.
Instructions file CodexOpenCode
Instructions for SethGammon/Citadel, covering codex harness, what this is, key conventions, testing and review guidelines.
Instructions file
Instructions for SethGammon/Citadel, covering claude harness, what this is, key conventions, testing and campaign design principles.
Agent
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 arbiter re-runs the objective gates itself (typecheck, tests, lint, the phase's command conditions) and judges holistic…
Agent
Read-only architecture reviewer. Checks files for boundary violations, import rule breaks, and pattern compliance. Does not modify files.
Agent
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 invocations. Does not write code — orchestrates those who do.
Agent
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 priorities. Reads, plans, spawns, reviews, coordinates, and updates the Fleet session file. Source code changes belong to…
Agent
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 afterward to integrate staged findings into the knowledge wiki.
Agent
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 files — read-only judge. Spawned by Archon after each phase and by Fleet after each wave agent.
Agent
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 modifies files — read-only judge. Spawned by Archon and Fleet before Red-reversibility operations.
Skill Claude CodeCodex
Replace with description of the skill and when Claude should use it.
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
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, quality judgment, and strategic decomposition.
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
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 step.
Skill Claude CodeCodex
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 user wants to encode a repeating workflow; do NOT use for one-off tasks or…
Skill Claude CodeCodex
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 schedules the next session. Auto-stops on campaign completion or budget…
Skill Claude CodeCodex
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 activity".
Skill Claude CodeCodex
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 for a single intake item. Resolved tickets graduate into .planning/intake/ for…