agentrigs
+ submit rig
~ / rigs / ahamedzoha / atelier

ahamedzoha/atelier

Learn-by-building template: turn any idea into a project you build by hand with an AI mentor. Works with Claude Code, Cursor, Copilot, Gemini & Codex. Toggle how much code the AI writes.

↗ GitHub ★ 3 MIT updated 4mo ago project Claude CodeCodexCursorGemini CLICopilot
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~3.2k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

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

$ npx degit ahamedzoha/atelier/.claude/skills/adr-review .claude/skills/adr-review
$ npx degit ahamedzoha/atelier/.claude/skills/lesson .claude/skills/lesson
$ npx degit ahamedzoha/atelier/.claude/skills/milestone .claude/skills/milestone
$ npx degit ahamedzoha/atelier/.claude/skills/mode .claude/skills/mode
$ npx degit ahamedzoha/atelier/.claude/skills/progress .claude/skills/progress
$ npx degit ahamedzoha/atelier/.claude/skills/start .claude/skills/start

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 (6)

adr-reviewlessonmilestonemodeprogressstart

Cursor rules (1)

methodology · always

Similar rigs

delbaoliveira/learn-claude-code
—
★ 183 project Claude Code 3 skills 8mo ago
Minimalist 1.2k tok ·
curtischoutw/claude-institution
After distilling Fable 5, the output is an indexed CLAUDE.md + on-demand rules + skills, an executable specification designed for weaker model sessions.
★ 5 project Claude Code 3 skills 6d ago
Minimalist 571 tok ·
Smolevich/pet-project-atlas
How to get your pet project found: search, AI search, content, distribution, analytics, money.
★ 2 project Claude CodeCodex 4 skills today
Minimalist 834 tok ·
Alenroyfeild/ai-dev-workspace
Shared task memory for AI coding assistants: Claude Code, Codex, Cursor, Copilot, Gemini CLI. Decisions survive sessions and assistants (benchmark: 5/5 vs 0/5). Plain Markdown you own, CLI + MCP.
★ 0 project Claude CodeCodex 4 skills today
Minimalist 652 tok ·
copied ✓