agentrigs
+ submit rig
~ / rigs / cadela-dev / ProjectAtlas

cadela-dev/ProjectAtlas

Claude Code workflow for mapping projects into clean-room behavior docs, file maps, batch reports, verification, and rebuild-ready blueprints.

↗ GitHub ★ 17 MIT updated 4mo ago project Claude Code
share on X
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
~1.0k tokens
Featherweight · 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 cadela-dev/ProjectAtlas/.claude ./rig-projectatlas  # 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 cadela-dev/ProjectAtlas/.claude/skills/architecture-synthesis .claude/skills/architecture-synthesis
$ npx degit cadela-dev/ProjectAtlas/.claude/skills/batch-planning .claude/skills/batch-planning
$ npx degit cadela-dev/ProjectAtlas/.claude/skills/clean-room-documentation .claude/skills/clean-room-documentation
$ npx degit cadela-dev/ProjectAtlas/.claude/skills/continue-batch-cycles .claude/skills/continue-batch-cycles
$ npx degit cadela-dev/ProjectAtlas/.claude/skills/index-fresh-project .claude/skills/index-fresh-project
$ npx degit cadela-dev/ProjectAtlas/.claude/skills/mirrored-file-docs .claude/skills/mirrored-file-docs
$ npx degit cadela-dev/ProjectAtlas/.claude/skills/repair-consistency .claude/skills/repair-consistency
$ npx degit cadela-dev/ProjectAtlas/.claude/skills/verification .claude/skills/verification
$ curl -fsSL --create-dirs -o .claude/agents/projectatlas-architect.md https://raw.githubusercontent.com/cadela-dev/ProjectAtlas/main/.claude/agents/projectatlas-architect.md
$ curl -fsSL --create-dirs -o .claude/agents/projectatlas-coordinator.md https://raw.githubusercontent.com/cadela-dev/ProjectAtlas/main/.claude/agents/projectatlas-coordinator.md
$ curl -fsSL --create-dirs -o .claude/agents/projectatlas-doc-worker.md https://raw.githubusercontent.com/cadela-dev/ProjectAtlas/main/.claude/agents/projectatlas-doc-worker.md
$ curl -fsSL --create-dirs -o .claude/agents/projectatlas-indexer.md https://raw.githubusercontent.com/cadela-dev/ProjectAtlas/main/.claude/agents/projectatlas-indexer.md
$ curl -fsSL --create-dirs -o .claude/agents/projectatlas-planner.md https://raw.githubusercontent.com/cadela-dev/ProjectAtlas/main/.claude/agents/projectatlas-planner.md
$ curl -fsSL --create-dirs -o .claude/agents/projectatlas-verifier.md https://raw.githubusercontent.com/cadela-dev/ProjectAtlas/main/.claude/agents/projectatlas-verifier.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 (8)

architecture-synthesisbatch-planningclean-room-documentationcontinue-batch-cyclesindex-fresh-projectmirrored-file-docsrepair-consistencyverification

Subagents (6)

projectatlas-architectBuild architecture understanding from verified docs only.
projectatlas-coordinatorRun planner, worker, verifier, architect loop until stop condition.
projectatlas-doc-workerDocument assigned files using mirrored paths and clean-room descriptions.
projectatlas-indexerCreate project inventory only; no documentation or architecture analysis.
projectatlas-plannerCreate the next safe assignment batch from unprocessed index entries.
projectatlas-verifierValidate worker outputs and update checklist state; never rewrite docs.

Similar rigs

Aurite-ai/agent-verifier
Agent Verifier is a coding agent skill that verifies code against organizational policies, code quality patterns, security requirements, and framework best practices — before code ships. Works with Claude Code, Cursor, Windsurf, and 30+ age
★ 3 project Claude Code 5 skills 6mo ago
Pragmatist 313 tok ·
Zack-Zz/ai-code
Complete ai Code configuration collection - agents, skills, hooks, commands, rules, MCPs. Battle-tested configs from an Anthropic hackathon winner.
★ 0 project Codex 7 skills today
Pragmatist 1.9k tok ·
lukehungngo/claude-mas-template
Production-grade multi-agent system template for Claude Code: 7 agents, 13 skills, TDD workflows, and battle-tested engineering practices
★ 0 project Claude Code 9 skills 6 hooks 5mo ago
Fort Knox 3.3k tok ·
TechDufus/dotfiles
Fully automated development environment for TechDufus using ansible.
★ 413 setup Claude CodeCodex 13 skills 1d ago
Skill Collector 1.2k tok ·
copied ✓