{"slug":"agentsatlas","title":"agentsatlas","description":"AgentsAtlas is a minimal, opinionated end-to-end workflow for Claude Code (also available as Codex skills). Eight slash commands take a project from setup through planning, execution, review, and milestone completion:\n\n/atlas:init, \n/atlas:plan, \n/atlas:execute,\n/atlas:status, \n/atlas:sync, \n/atlas:triage, \n/atlas:review, \n/atlas:complete. \n/atlas:execute \n\nRuns each 3–5-task plan in a fresh subagent (clean ~200k-token context) so quality doesn't degrade across a long run, while a small CLAUDE.md plus .planning/STATE.md and ROADMAP.md keep session continuity without context bloat. \n\nIt also ships 16 development \"discipline\" skills: debugging, testing,\nverifying, refactoring, security-audit, scaffolding, committing, creating-pr, and more enforcing root-cause-first investigation, evidence-before-claims verification, and test-first development. \n\n# Install globally (available in all projects)\nnpx agents-atlas --global\n\n# Or install locally (current project only)\nnpx agents-atlas --local\n\nMIT licensed; no telemetry, no network calls beyond Anthropic, and no bypass-permissions requirement.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-05T06:02:20.671Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/AvinashP/AgentsAtlas.git","web_data":{},"github_data":{},"catalog_sources":{"community":[{"name":"agentsatlas","source":{"sha":"72e52289e6c42e45dab5870a86d9c3b914f94fdd","url":"https://github.com/AvinashP/AgentsAtlas.git","source":"url"},"homepage":"https://github.com/AvinashP/AgentsAtlas#readme","description":"AgentsAtlas is a minimal, opinionated end-to-end workflow for Claude Code (also available as Codex skills). Eight slash commands take a project from setup through planning, execution, review, and milestone completion:\n\n/atlas:init, \n/atlas:plan, \n/atlas:execute,\n/atlas:status, \n/atlas:sync, \n/atlas:triage, \n/atlas:review, \n/atlas:complete. \n/atlas:execute \n\nRuns each 3–5-task plan in a fresh subagent (clean ~200k-token context) so quality doesn't degrade across a long run, while a small CLAUDE.md plus .planning/STATE.md and ROADMAP.md keep session continuity without context bloat. \n\nIt also ships 16 development \"discipline\" skills: debugging, testing,\nverifying, refactoring, security-audit, scaffolding, committing, creating-pr, and more enforcing root-cause-first investigation, evidence-before-claims verification, and test-first development. \n\n# Install globally (available in all projects)\nnpx agents-atlas --global\n\n# Or install locally (current project only)\nnpx agents-atlas --local\n\nMIT licensed; no telemetry, no network calls beyond Anthropic, and no bypass-permissions requirement."}]}}