citadel

Heads-up on Anthropic's routine quota: Claude Code accounts are limited to 15 routine runs per rolling 24 hours (CronCreate / ScheduleWakeup / RemoteTrigger). A single /watch or /daemon can exhaust it quickly and pause unrelated routines on your account. Citadel ships local, quota-free runners for each of those features — see docs/ROUTINE-QUOTA.md.

What Is Citadel

An agent orchestration harness for Claude Code and OpenAI Codex. It coordinates multiple AI agents in parallel, persists memory across sessions, and routes your intent to the cheapest execution path automatically. Citadel adapts itself to each runtime: plugin-first for Claude Code, generated project artifacts plus Codex-native config for Codex.

Why Citadel Exists

Without Citadel, every agent session starts from zero. You re-explain architecture decisions. You re-discover that the auth module is fragile. You copy-paste the same review checklist. When a task is too big for one agent, you manually split it and lose context between the pieces. Your agents never get better at your codebase — you just get better at prompting them.

With Citadel, sessions resume where they left off. A /do review runs a structured 5-pass review that remembers what broke last time. A /do overhaul the API layer spawns parallel agents in isolated worktrees, shares discoveries between them, and merges the results. Skills you build once compound across every future session. The system learns from its own mistakes through campaign persistence and telemetry.

The difference: CLAUDE.md and AGENTS.md tell the runtime about your project. Citadel gives the runtime the infrastructure to work autonomously — routing, memory, safety hooks, and coordination that a single guidance file can't provide.

Quickstart

Prerequisites: Claude Code or Codex + Node.js 18+

# 1. Clone Citadel
git clone https://github.com/SethGammon/Citadel.git

# 2a. Claude Code runtime
claude --plugin-dir /path/to/Citadel

# 2b. Codex runtime
node /path/to/Citadel/scripts/codex-compat.js
node /path/to/Citadel/scripts/install-hooks-codex.js
codex

# 3. In either runtime, run setup
/do setup

# 4. Try something
/do review src/main.ts

Quickstart for both runtimes · Claude Code installation guide · Codex installation guide · Share what you're building →

How It Works

Say what you want. /do routes it to the cheapest tool that can handle it.

/do fix the typo on line 42        # Direct edit, no model call
/do review the auth module         # 5-pass structured code review
/do why is the API returning 500   # Root cause analysis
/do build a caching layer          # Multi-step orchestrated build
/do overhaul all three services    # Parallel fleet with isolated worktrees

Classification runs across four tiers, each cheaper than the last:

1. Pattern match — catches trivial commands with regex. Zero tokens, zero model calls, instant.
2. Session state — checks if you're mid-campaign and resumes it. Still zero tokens.
3. Keyword lookup — scans your input against installed skill keywords ("review", "test", "refactor") and routes directly. Still zero tokens.
4. LLM classification — only when tiers 1-3 don't match, a structured complexity analysis (~500 tokens) determines whether you need a single-step Marshal, a multi-session Archon, or a parallel Fleet.

Most requests resolve at tiers 1-3 for free. Tier 4 is the exception, not the default. You never have to choose the tool.