agentrigs
+ submit rig
~ / rigs / liteman / cc-atelier

liteman/cc-atelier

Structured design workflow workspace for Claude Code — 7-phase design thinking with templates, agents, and assumption challenger

↗ GitHub ★ 0 MIT updated 3d ago project Claude CodeCodex
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~2.4k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
2/5
Blocks destructive commands · No YOLO mode · details

Copy this rig

# review before running: this installs third-party code
$ npx degit liteman/cc-atelier/.claude ./rig-cc-atelier  # 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.

$ curl -fsSL --create-dirs -o .claude/agents/challenger.md https://raw.githubusercontent.com/liteman/cc-atelier/main/.claude/agents/challenger.md
$ curl -fsSL --create-dirs -o .claude/agents/user-advocate.md https://raw.githubusercontent.com/liteman/cc-atelier/main/.claude/agents/user-advocate.md
$ curl -fsSL --create-dirs -o .claude/agents/ux-critic.md https://raw.githubusercontent.com/liteman/cc-atelier/main/.claude/agents/ux-critic.md

Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.

{
  "permissions": {
    "deny": [
      "Bash(rm -rf /:*)",
      "Bash(rm -rf /Users:*)",
      "Bash(rm -rf ~:*)",
      "Bash(rm -rf $HOME:*)",
      "Bash(rm -rf /System:*)",
      "Bash(rm -rf /Library:*)",
      "Bash(rm -rf /Applications:*)",
      "Bash(rm -rf /Volumes:*)",
      "Bash(rm -rf /etc:*)",
      "Bash(rm -rf /var:*)",
      "Bash(rm -rf /usr:*)",
      "Bash(rm -rf /opt:*)",
      "Bash(rm -r /:*)",
      "Bash(rm -r /Users:*)",
      "Bash(rm -r ~:*)",
      "Bash(rm -r $HOME:*)",
      "Bash(rm -r /System:*)",
      "Bash(rm -r /Library:*)",
      "Bash(rm -r /Applications:*)",
      "Bash(rm -r /Volumes:*)",
      "Bash(rm -fr /:*)",
      "Bash(rm -fr /Users:*)",
      "Bash(rm -fr ~:*)",
      "Bash(rm -fr $HOME:*)",
      "Bash(rm -fr /System:*)",
      "Bash(rm -fr /Library:*)",
      "Bash(rm -fr /Applications:*)",
      "Bash(rm -fr /Volumes:*)",
      "Bash(git push --force:*)",
      "Bash(git push -f:*)",
      "Bash(git reset --hard:*)"
    ]
  }
}

Subagents (3)

challenger
model: opus
Adversarial thinking partner that challenges assumptions and argues counter-positions
user-advocate
model: sonnet
Role-plays the target user persona to provide qualitative UX feedback
ux-critic
model: sonnet
Evaluates UI/UX designs against Nielsen's heuristics and WCAG 2.2 AA

Slash commands (10)

/challenge/checkpoint/define-agent/finalize-design/load-design-phase/resume-design/start-design-session/start-ux-session/team-status/verify-context

Permissions

deny (31)
Bash(rm -rf /:*)
Bash(rm -rf /Users:*)
Bash(rm -rf ~:*)
Bash(rm -rf $HOME:*)
Bash(rm -rf /System:*)
Bash(rm -rf /Library:*)
Bash(rm -rf /Applications:*)
Bash(rm -rf /Volumes:*)
Bash(rm -rf /etc:*)
Bash(rm -rf /var:*)
Bash(rm -rf /usr:*)
Bash(rm -rf /opt:*)
Bash(rm -r /:*)
Bash(rm -r /Users:*)
Bash(rm -r ~:*)
Bash(rm -r $HOME:*)
Bash(rm -r /System:*)
Bash(rm -r /Library:*)
Bash(rm -r /Applications:*)
Bash(rm -r /Volumes:*)
Bash(rm -fr /:*)
Bash(rm -fr /Users:*)
Bash(rm -fr ~:*)
Bash(rm -fr $HOME:*)
Bash(rm -fr /System:*)
Bash(rm -fr /Library:*)
Bash(rm -fr /Applications:*)
Bash(rm -fr /Volumes:*)
Bash(git push --force:*)
Bash(git push -f:*)
Bash(git reset --hard:*)
ask (0)
—
allow (16)
Bash(ls:*)
Bash(pwd:*)
Bash(tree:*)
Bash(file:*)
Bash(which:*)
Bash(git status:*)
Bash(git diff:*)
Bash(git log:*)
Bash(git show:*)
Bash(git branch:*)
Bash(git remote:*)
Bash(git add:*)
Bash(git commit:*)
Bash(curl:*)
WebFetch
WebSearch

Similar rigs

MiguelAxcar/ai-rpi-protocol
Repo-native protocol for AI-assisted coding that enforces a simple discipline: research first, plan second, code last. Drop it into any repository to reduce wrong implementations, cut rewrite cycles, and improve decisions earlier in the wor
★ 28 project Claude CodeCodex 15 agents 7mo ago
Orchestrator 2.3k tok ·
liatrio-labs/claude-code-gauntlet
Adversarial code review for Claude Code: each GitHub PR or GitLab MR runs a gauntlet of up to seven specialist agents for bugs, security, tests and cross-file impact, and every finding must survive verification, a skeptical validator, and a
★ 12 project Claude CodeCodex 3 skills 12 agents 1 hooks today
Orchestrator 1.6k tok ·
mim1963/mim-CC-dev-bootstrap
Claude Code multi-agent dev environment pieces
★ 0 project Claude Code 54 agents 8 hooks 7mo ago
Orchestrator 5.8k tok ·
bmubook/ag-launchpad-ar
⁧⚡ قالب إقلاع عربي للمبتدئين يحوّل Claude Code و OpenCode و Cursor و Google Antigravity إلى مهندس منضبط: قواعد حاكمة، إنفاذ آلي، رحلة موجّهة بخارطة طريق مرئية، ومخططات Firebase جاهزة — وعندك مشروع؟ ركّب فيه «الحارس» فلا يقول لك الوكيل «تم»
★ 0 project Claude CodeCodex 16 skills 3 agents 5 hooks 2d ago
Fort Knox 13.7k tok ·
copied ✓