Browse / Software development / Software-Engineer-AI-Agent-Atlas

Software-Engineer-AI-Agent-Atlas

syahiidkamil

ATLAS: a senior-engineer layer for Claude Code.

Open syahiidkamil/Software-Engineer-AI-Agent-Atlas → Does not match the four rules.

ai-agentai-coding-assistantai-software-engineeranthropicclaudeclaude-codeclaude-code-agentsclaude-code-skillsclaude-code-templatecoding-agentdeveloper-toolsllm

Built for Claude Code

ships .claude CLAUDE.md and nothing for other agents.

In its own words

Aboutsyahiidkamil/Software-Engineer-AI-Agent-Atlas

Explore with wireframes & prototypes, clarify the essentials, capture it in HTML spec doc then let Claude Code's native plan/goal/workflow loop build. Fewer tokens, less ceremony, faster to what people pictured. KISS/YAGNI/DRY, context decides. No overengineering. Clean architecture that works.

README.md

The senior-engineer layer for Claude Code. Explore before you build, clarify only what matters, capture it in living HTML, then hand it to Claude Code's native plan / goal / workflow loop. Fewer tokens, less ceremony, faster to the thing people actually pictured.

One command. Full setup. No copy-pasting prompts every session.

ATLAS is an open-source Claude Code template: a curated set of skills, subagents, slash commands, and engineering conventions that turn Claude Code into a production-grade AI software engineer, with a wireframe-and-prototype workflow in place of heavyweight spec-driven development.

It ships in three CLAUDE.md modes, so you choose how much of the wheel to hand over:

  • Vanilla — minimal footprint, no ATLAS identity.
  • Collaborative (default) — the full senior-engineer identity with a review-and-commit loop; you stay in the driver's seat.
  • Autonomous — the approval loop removed and **free-will** wired in (alongside super-product-owner and super-ui-ux-design): the skill that lets ATLAS decide for itself on the high-stakes forks — hold real alternatives open, ground each in evidence, refute the winner, then log the call in docs/decision_logs/. That's what lets it one-shot an app and run unattended without going off the rails.

The repository's own description, then 10% of its README. Read the rest on GitHub ↗

What came from it 6

inspired by nekuloZ/agent-memory +memory +scripts A four-layer memory system for AI agents 5 months ago
inspired by the-sid-dani/second-brain-os +memory +scripts +workspace PARA second-brain OS for Claude Code — fork, /bootstrap, done. 18 days ago
inspired by kv0906/pm-kit +00-inbox +01-index +_archive +_core +_templates +blockers +cli +daily +decisions +examples +handbook +meetings +reports +scripts +.claude-plugin +.cursor AI-augmented PM workspace for Coding Agents — daily standups, decisions, blockers, docs, and sprint reviews as markdown last month
inspired by hAcKlyc/openmino +memory A ready-to-use workspace template that turns any AI agent into a persistent, evolving companion. 5 months ago
inspired by luka-commits/startup-setup +_tmp +context +inbox +projects +reference +tools Startup-Setup: persönliches Claude-Code-Workspace-Paket (offene Variante) — Daily Briefing, Mail-Triage, Projekt-Trackin 9 days ago
adapted 0xlucian/agent-workspace-template +memory +scripts A template repository for setting up a Claude Code operations agent that manages multiple repositories, infrastructure, 3 months ago

Read from the repository's git tree on 2026-08-17.