SethGammon/Citadel
The operating layer for Claude Code + OpenAI Codex: persistent project memory, intent routing, safety hooks, cost telemetry, and parallel agent fleets.
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code $ claude mcp add _github -e GITHUB_<redacted> -- npx -y @modelcontextprotocol/server-github $ claude mcp add _filesystem -- npx -y @modelcontextprotocol/server-filesystem . $ claude mcp add _git -- uvx 'mcp-server-git@>=2025.12.18' --repository . $ npx degit SethGammon/Citadel/agents ./rig-citadel/agents $ npx degit SethGammon/Citadel/skills ./rig-citadel/skills $ npx degit SethGammon/Citadel/hooks ./rig-citadel/hooks
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ claude mcp add _github -e GITHUB_<redacted> -- npx -y @modelcontextprotocol/server-github $ claude mcp add _filesystem -- npx -y @modelcontextprotocol/server-filesystem . $ claude mcp add _git -- uvx 'mcp-server-git@>=2025.12.18' --repository .
$ npx degit SethGammon/Citadel/skills/architect .claude/skills/architect $ npx degit SethGammon/Citadel/skills/archon .claude/skills/archon $ npx degit SethGammon/Citadel/skills/ascii-diagram .claude/skills/ascii-diagram $ npx degit SethGammon/Citadel/skills/autopilot .claude/skills/autopilot $ npx degit SethGammon/Citadel/skills/cost .claude/skills/cost $ npx degit SethGammon/Citadel/skills/create-app .claude/skills/create-app $ npx degit SethGammon/Citadel/skills/create-skill .claude/skills/create-skill $ npx degit SethGammon/Citadel/skills/daemon .claude/skills/daemon $ npx degit SethGammon/Citadel/skills/dashboard .claude/skills/dashboard $ npx degit SethGammon/Citadel/skills/decision-map .claude/skills/decision-map $ npx degit SethGammon/Citadel/skills/deploy-steward .claude/skills/deploy-steward $ npx degit SethGammon/Citadel/skills/design .claude/skills/design $ npx degit SethGammon/Citadel/skills/do .claude/skills/do $ npx degit SethGammon/Citadel/skills/doc-gen .claude/skills/doc-gen $ npx degit SethGammon/Citadel/skills/evolve .claude/skills/evolve $ npx degit SethGammon/Citadel/skills/experiment .claude/skills/experiment $ npx degit SethGammon/Citadel/skills/fleet .claude/skills/fleet $ npx degit SethGammon/Citadel/skills/grill .claude/skills/grill $ npx degit SethGammon/Citadel/skills/houseclean .claude/skills/houseclean $ npx degit SethGammon/Citadel/skills/improve .claude/skills/improve $ npx degit SethGammon/Citadel/skills/infra-audit .claude/skills/infra-audit $ npx degit SethGammon/Citadel/skills/learn .claude/skills/learn $ npx degit SethGammon/Citadel/skills/live-preview .claude/skills/live-preview $ npx degit SethGammon/Citadel/skills/loop .claude/skills/loop $ npx degit SethGammon/Citadel/skills/map .claude/skills/map $ npx degit SethGammon/Citadel/skills/marshal .claude/skills/marshal $ npx degit SethGammon/Citadel/skills/merge-review .claude/skills/merge-review $ npx degit SethGammon/Citadel/skills/organize .claude/skills/organize $ npx degit SethGammon/Citadel/skills/postmortem .claude/skills/postmortem $ npx degit SethGammon/Citadel/skills/pr-watch .claude/skills/pr-watch $ npx degit SethGammon/Citadel/skills/prd .claude/skills/prd $ npx degit SethGammon/Citadel/skills/qa .claude/skills/qa $ npx degit SethGammon/Citadel/skills/refactor .claude/skills/refactor $ npx degit SethGammon/Citadel/skills/research .claude/skills/research $ npx degit SethGammon/Citadel/skills/review .claude/skills/review $ npx degit SethGammon/Citadel/skills/scaffold .claude/skills/scaffold $ npx degit SethGammon/Citadel/skills/schedule .claude/skills/schedule $ npx degit SethGammon/Citadel/skills/session-handoff .claude/skills/session-handoff $ npx degit SethGammon/Citadel/skills/setup .claude/skills/setup $ npx degit SethGammon/Citadel/skills/systematic-debugging .claude/skills/systematic-debugging
$ curl -fsSL --create-dirs -o .claude/agents/arbiter.md https://raw.githubusercontent.com/SethGammon/Citadel/main/agents/arbiter.md $ curl -fsSL --create-dirs -o .claude/agents/arch-reviewer.md https://raw.githubusercontent.com/SethGammon/Citadel/main/agents/arch-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/archon.md https://raw.githubusercontent.com/SethGammon/Citadel/main/agents/archon.md $ curl -fsSL --create-dirs -o .claude/agents/fleet.md https://raw.githubusercontent.com/SethGammon/Citadel/main/agents/fleet.md $ curl -fsSL --create-dirs -o .claude/agents/knowledge-extractor.md https://raw.githubusercontent.com/SethGammon/Citadel/main/agents/knowledge-extractor.md $ curl -fsSL --create-dirs -o .claude/agents/phase-validator.md https://raw.githubusercontent.com/SethGammon/Citadel/main/agents/phase-validator.md $ curl -fsSL --create-dirs -o .claude/agents/policy-enforcer.md https://raw.githubusercontent.com/SethGammon/Citadel/main/agents/policy-enforcer.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 6,413 rigs:
{
"permissions": {
"deny": [
"Read(~/.ssh/**)",
"Read(**/.env)",
"Bash(rm -rf *)",
"Read(./.env)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(**/*.pem)",
"Bash(rm -rf /*)",
"Read(~/.aws/**)",
"Bash(rm -rf:*)",
"Read(.env)",
"Bash(git push --force*)",
"Read(**/*.key)",
"Read(./.env.*)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(gh pr merge *)",
"Bash(chown *)",
"Bash(docker *)"
]
}
} MCP servers (5)
| server | source | est. tokens |
|---|---|---|
| citadel-state env: CITADEL_MCP_SERVER | local / custom | 2.5k |
| codebase-memory env: CITADEL_MCP_SERVER | local / custom | 2.5k |
| GitHub MCP · "_github" env: GITHUB_TOKEN | npm | 18.0k |
| Filesystem · "_filesystem" | npm | 4.2k |
| Git · "_git" | pypi | 3.2k |
Skills (48)
architectarchonascii-diagramautopilotcostcreate-appcreate-skilldaemondashboarddecision-mapdeploy-stewarddesigndodoc-genevolveexperimentfleetgrillhousecleanimproveinfra-auditlearnlive-previewloopmapmarshalmerge-revieworganizepostmortempr-watchprdqarefactorresearchreviewscaffoldschedulesession-handoffsetupsystematic-debuggingtelemetrytest-gentriageunharnessverifywatchwikiworkspace
Subagents (7)
| arbiter model: fable | >- |
| arch-reviewer | >- |
| archon model: opus | >- |
| fleet model: opus | >- |
| knowledge-extractor | >- |
| phase-validator model: claude-haiku-4-5 | >- |
| policy-enforcer model: claude-haiku-4-5 | >- |
Similar rigs
JoaoPeixoto72/production-quality-ready
Sistema de qualidade e auditoria com gates declarativos para Antigravity e Claude Code
Skill Collector 2.1k tok ·
iamvonpasion/hashb
Dev workflow toolkit for Claude Code — 14 skills that turn AI into a structured development partner. Spec → Design → Eng → TDD → Review → QA → Ship.
Skill Collector 2.5k tok ·
NeamulMorshed/The-Monkey-Brain
—
Skill Collector 11.6k tok ·
heliohq/ship
An agentic development harness for Claude Code, Codex & Cursor: gated pipeline from spec to green checks.
Skill Collector 3.7k tok ·