Whiskey-Tango-Foxtrot-GmbH/sisyclaude
An attempt to make claude code smarter by adapting oh-my-openagent's amazing agentic setup.
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code $ npx degit Whiskey-Tango-Foxtrot-GmbH/sisyclaude/agents ./rig-sisyclaude/agents $ npx degit Whiskey-Tango-Foxtrot-GmbH/sisyclaude/skills ./rig-sisyclaude/skills
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.
$ npx degit Whiskey-Tango-Foxtrot-GmbH/sisyclaude/skills/activate .claude/skills/activate $ npx degit Whiskey-Tango-Foxtrot-GmbH/sisyclaude/skills/brainstorm .claude/skills/brainstorm $ npx degit Whiskey-Tango-Foxtrot-GmbH/sisyclaude/skills/deactivate .claude/skills/deactivate
$ curl -fsSL --create-dirs -o .claude/agents/atlas.md https://raw.githubusercontent.com/Whiskey-Tango-Foxtrot-GmbH/sisyclaude/main/agents/atlas.md $ curl -fsSL --create-dirs -o .claude/agents/explore.md https://raw.githubusercontent.com/Whiskey-Tango-Foxtrot-GmbH/sisyclaude/main/agents/explore.md $ curl -fsSL --create-dirs -o .claude/agents/hephaestus.md https://raw.githubusercontent.com/Whiskey-Tango-Foxtrot-GmbH/sisyclaude/main/agents/hephaestus.md $ curl -fsSL --create-dirs -o .claude/agents/librarian.md https://raw.githubusercontent.com/Whiskey-Tango-Foxtrot-GmbH/sisyclaude/main/agents/librarian.md $ curl -fsSL --create-dirs -o .claude/agents/metis.md https://raw.githubusercontent.com/Whiskey-Tango-Foxtrot-GmbH/sisyclaude/main/agents/metis.md $ curl -fsSL --create-dirs -o .claude/agents/momus.md https://raw.githubusercontent.com/Whiskey-Tango-Foxtrot-GmbH/sisyclaude/main/agents/momus.md $ curl -fsSL --create-dirs -o .claude/agents/oracle.md https://raw.githubusercontent.com/Whiskey-Tango-Foxtrot-GmbH/sisyclaude/main/agents/oracle.md $ curl -fsSL --create-dirs -o .claude/agents/prometheus.md https://raw.githubusercontent.com/Whiskey-Tango-Foxtrot-GmbH/sisyclaude/main/agents/prometheus.md $ curl -fsSL --create-dirs -o .claude/agents/socrates.md https://raw.githubusercontent.com/Whiskey-Tango-Foxtrot-GmbH/sisyclaude/main/agents/socrates.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"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(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Skills (3)
Subagents (9)
| atlas model: opus | Plan executor and orchestrator that delegates ALL implementation via sub-agents. Never writes code itself. Reads plans, builds parallelization maps, delegates tasks, and rigorously verifies every resu |
| explore model: haiku | Fast codebase search specialist. Answers "Where is X?", "Which file has Y?", "Find the code that does Z". Fire multiple in parallel for broad searches. (Explore - SisyClaude Plugin) |
| hephaestus model: opus | Autonomous deep worker that never asks permission and keeps going until 100% done. Senior Staff Engineer persona. Use for deep implementation tasks, complex bug fixes, and end-to-end feature work. Fir |
| librarian model: sonnet | Open-source codebase understanding agent for documentation lookup, library research, and finding implementation examples using GitHub CLI, web search, and documentation fetching. (Librarian - SisyClau |
| metis model: opus | Pre-planning consultant that analyzes requests to identify hidden intentions, ambiguities, and AI failure points before planning begins. Use for complex or ambiguous requests. (Metis - SisyClaude Plug |
| momus model: sonnet | Plan reviewer that checks executability and reference validity. Approval-biased — only rejects for true blockers. Use after Prometheus creates a plan, before execution. (Momus - SisyClaude Plugin) |
| oracle model: opus | Read-only architecture consultant for complex decisions, hard debugging, and self-review. Use for multi-system tradeoffs, after 2+ failed fix attempts, or unfamiliar code patterns. (Oracle - SisyClaud |
| prometheus model: opus | Strategic planning consultant that interviews users, gathers requirements, and produces detailed work plans. Does NOT write code — only creates plans in .claude/plans/. Use for any non-trivial task th |
| socrates model: opus | Adversarial-constructive design critic for interactive idea stress-testing. Challenges assumptions, surfaces trade-offs, and sharpens thinking through Socratic dialogue. Writes a handoff draft for Pro |
Similar rigs
andrewhampton/dotfiles
My dotfiles
Minimalist 1.3k tok ·
jangtrinh/design-os
Design CLI for Claude Code, Codex and Antigravity: describe the UI in plain words, get production-grade web, Figma and SwiftUI output through deterministic taste gates.
Pragmatist 3.3k tok ·
code-yeongyu/my-claude-code-harness
I'm confident this setup will become deprecated and outdated in less than 3 months
Pragmatist 2.8k tok ·
JulesNsenda/claude-workflow
My global Claude Code config — a plan → gate → commit workflow with adversarial review, symlinked into ~/.claude
Fort Knox 3.8k tok ·