shoklah/roland
An agentic workflow template for Claude Code: hooks, custom agents and a CLAUDE.md section
stack: Python
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 shoklah/roland/agents ./rig-roland/agents $ npx degit shoklah/roland/skills ./rig-roland/skills $ npx degit shoklah/roland/hooks ./rig-roland/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.
$ npx degit shoklah/roland/skills/workflow-dashboard .claude/skills/workflow-dashboard $ curl -fsSL --create-dirs -o .claude/agents/final-reviewer.md https://raw.githubusercontent.com/shoklah/roland/main/agents/final-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/fix-checker.md https://raw.githubusercontent.com/shoklah/roland/main/agents/fix-checker.md $ curl -fsSL --create-dirs -o .claude/agents/implementer-copy.md https://raw.githubusercontent.com/shoklah/roland/main/agents/implementer-copy.md $ curl -fsSL --create-dirs -o .claude/agents/implementer-escalated.md https://raw.githubusercontent.com/shoklah/roland/main/agents/implementer-escalated.md $ curl -fsSL --create-dirs -o .claude/agents/implementer.md https://raw.githubusercontent.com/shoklah/roland/main/agents/implementer.md $ curl -fsSL --create-dirs -o .claude/agents/kit-reviewer.md https://raw.githubusercontent.com/shoklah/roland/main/agents/kit-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/plan-reviewer.md https://raw.githubusercontent.com/shoklah/roland/main/agents/plan-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/plan-simplifier.md https://raw.githubusercontent.com/shoklah/roland/main/agents/plan-simplifier.md $ curl -fsSL --create-dirs -o .claude/agents/sweeper.md https://raw.githubusercontent.com/shoklah/roland/main/agents/sweeper.md $ curl -fsSL --create-dirs -o .claude/agents/task-reviewer.md https://raw.githubusercontent.com/shoklah/roland/main/agents/task-reviewer.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 (1)
Subagents (10)
| final-reviewer model: opus | Fresh review of a whole branch after simplify, for the Full path's final review and the Small path's one reviewer. |
| fix-checker model: sonnet | Re-checks whether specific listed review findings are fixed, in a fix round or after the final review's fix wave. |
| implementer-copy model: sonnet | Implements one plan task whose text already holds the function bodies, not just signatures and tests. |
| implementer-escalated model: fable | Fresh round 3 implementer one tier up from Opus, for a task whose findings or checks are still open after two rounds. |
| implementer model: opus | Implements one task of an approved plan; the default implementer in subagent-driven-development. |
| kit-reviewer model: opus | A kit's own review of one implemented task, or of a Small path branch, against the kit's checklist. |
| plan-reviewer model: fable | One-pass review of an implementation plan against its spec and the repo, before the owner approves the plan. |
| plan-simplifier model: opus | One-pass check of an implementation plan for excess, before plan review, so the planning session can slim it first. |
| sweeper model: haiku | Does a read-only lookup of five or more reads for the main session and reports only its conclusion, each fact with where it was read. |
| task-reviewer model: opus | Fresh review of one implemented plan task, after its automated checks pass. |
Similar rigs
shoklah/claude-workflow-template
An agentic workflow template for Claude Code: hooks, custom agents and a CLAUDE.md section
Orchestrator 3.8k tok · · Q0
jblossey/houserules
A CLI that makes your AI coding agents adhere to your rules, audits each change, and proves your intent is obeyed.
Orchestrator 3.6k tok · · Q15
zmilojevic/hearth
Keep your Claude Code sessions warm. Desktop app for Claude Code, Linux-first (also macOS/Windows): all your sessions in one sidebar, diffs, terminal, cache keep-warm, phone companion. Uses your Claude subscription, no API key.
Pragmatist 14.7k tok · · Q25
yellow-pine/noggin
Animatronic CyberBrick head that reacts to Claude Code
Minimalist 1.5k tok · · Q29