softagram/goodreason-agents-setup
GoodReason agent topology for Claude Code: four subagents (Strategist, Architect, Implementer, Evolution) with scoped verdict authority over the eight α–Ω anchors
stack: Shell
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 softagram/goodreason-agents-setup/.claude ./rig-goodreason-agents-setup # inspect, then merge into .claude/ 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 softagram/goodreason-agents-setup/skills/cycle-review .claude/skills/cycle-review $ npx degit softagram/goodreason-agents-setup/skills/cycle-team-experimental .claude/skills/cycle-team-experimental $ npx degit softagram/goodreason-agents-setup/skills/cycle .claude/skills/cycle $ npx degit softagram/goodreason-agents-setup/skills/goodreason-ontology .claude/skills/goodreason-ontology
$ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/softagram/goodreason-agents-setup/main/.claude/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/evolution.md https://raw.githubusercontent.com/softagram/goodreason-agents-setup/main/.claude/agents/evolution.md $ curl -fsSL --create-dirs -o .claude/agents/implementer.md https://raw.githubusercontent.com/softagram/goodreason-agents-setup/main/.claude/agents/implementer.md $ curl -fsSL --create-dirs -o .claude/agents/strategist.md https://raw.githubusercontent.com/softagram/goodreason-agents-setup/main/.claude/agents/strategist.md $ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/softagram/goodreason-agents-setup/main/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/evolution.md https://raw.githubusercontent.com/softagram/goodreason-agents-setup/main/agents/evolution.md $ curl -fsSL --create-dirs -o .claude/agents/implementer.md https://raw.githubusercontent.com/softagram/goodreason-agents-setup/main/agents/implementer.md $ curl -fsSL --create-dirs -o .claude/agents/strategist.md https://raw.githubusercontent.com/softagram/goodreason-agents-setup/main/agents/strategist.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (4)
Subagents (8)
| Architect model: opus | Governs logic (pi) and structure (beta). Responsible for conceptual integrity of the system. |
| Evolution model: opus | Governs feedback (omega) and change pressure (delta-psi). Responsible for quality and continuous improvement. |
| Implementer model: opus | Governs solution (phi) and implementation (tau). Responsible for writing code and connecting modules. |
| Strategist model: opus | Governs purpose (alpha) and environment (chi). Answers "why" and "against what". |
| Architect model: opus | Governs logic (pi) and structure (beta). Responsible for conceptual integrity of the system. |
| Evolution model: opus | Governs feedback (omega) and change pressure (delta-psi). Responsible for quality and continuous improvement. |
| Implementer model: opus | Governs solution (phi) and implementation (tau). Responsible for writing code and connecting modules. |
| Strategist model: opus | Governs purpose (alpha) and environment (chi). Answers "why" and "against what". |
Similar rigs
yuroka-studio/nightshift-agents
Scheduled Claude Code agents that take one task from a backlog, open a PR with real test evidence, and never merge or deploy on their own.
Fort Knox 1.0k tok · · Q61
ufukyuksel-dev/SUPER_COMPUTER_AI
Build your own super AI: skills, MCP servers, agent roles and instructions for Claude Code and Codex, installed with one reversible command.
Orchestrator 806 tok · · Q5
Trolzie/claude-loop-systems-demo
A small demo of Markdown-as-system AI dev loops with Claude Code: issues → agents → skills → verification.
Pragmatist 480 tok · · Q15
homeofe/improvements
Portable, LLM-agnostic framework for multi-model AI workflows: model routing, structured agent handoff (AAHP), and a phased agent pipeline. MIT.
Orchestrator 1.4k tok · · Q24