Agent Plugins Marketplace
← All plugins

atomlane

v0.17.0

AtomLane combines a universal safety core with platform-native, workload-tailored parallel execution on macOS Stable and native Windows Preview.

Codex2 Skills1 MCP serverstdio

By cloudguo123License: MPL-2.01.1k GitHub starsUpdated 12 hours ago

Directory evidence

Runtimes
Codex
Parsed components
3 skill or MCP entries
Source updated
Sep 23, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install atomlane for Codex

Installs for the current user
codex plugin marketplace add hashgraph-online/awesome-codex-plugins
codex plugin marketplace upgrade awesome-codex-plugins
codex plugin add atomlane@awesome-codex-plugins

Paste and run these commands in a terminal with Codex. They add and refresh the awesome-codex-plugins catalog, then install this plugin.

Compatibility: the page URL and API slug “atomlane” remain stable.

  • Codex: atomlane@agent-plugin-marketplace → atomlane@awesome-codex-plugins

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/hashgraph-online/awesome-codex-plugins

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/cloudguo123/atomlane/.

Plugin files

plugins/cloudguo123/atomlane/
├── .codex-plugin/plugin.json
├── skills/accelerate-local-work/SKILL.md
├── skills/optimize-python-parallelism/SKILL.md
└── .mcp.json

Included Skills2

accelerate-local-workskills/accelerate-local-work/SKILL.md

Use AtomLane to compile and execute safe atomic parallel plans on macOS and native Windows Preview for worthwhile independent argv tasks, dependency DAGs, supported platform entrypoints, or Apple-silicon operators. Use at task start or an execution boundary when structured local work may contain two or more worthwhile units; skip plain answers, one quick command, and work whose effects cannot be safely bounded.

optimize-python-parallelismskills/optimize-python-parallelism/SKILL.md

Analyze and, when the task authorizes source optimization, refactor a concrete long-running Python entrypoint containing repeated independent work. Use for explicit Python speedup or parallelization requests and evidence-backed long-running entrypoints; skip ordinary Python edits, test execution alone, short scripts, and projects that merely contain Python files.

MCP servers1

atomlanestdio
command
python3
args
./scripts/mcp_server.py
cwd
.

Plugin manifests1

plugins/cloudguo123/atomlane/.codex-plugin/plugin.json
{
  "name": "atomlane",
  "version": "0.17.0",
  "description": "AtomLane combines a universal safety core with platform-native, workload-tailored parallel execution on macOS Stable and native Windows Preview.",
  "author": {
    "name": "cloudguo123",
    "url": "https://github.com/cloudguo123"
  },
  "homepage": "https://cloudguo123.github.io/atomlane/",
  "repository": "https://github.com/cloudguo123/atomlane",
  "license": "MPL-2.0",
  "keywords": [
    "macos",
    "windows",
    "cross-platform",
    "workload-optimization",
    "parallel",
    "pytest",
    "pytest-xdist",
    "scheduler",
    "atomic-planning",
    "effect-analysis",
    "python",
    "static-analysis",
    "refactoring",
    "scenario-planning",
    "local-execution",
    "performance"
  ],
  "skills": "./skills/",
  "interface": {
    "displayName": "AtomLane",
    "shortDescription": "Universal-safe, workload-tailored parallelism",
    "longDescription": "AtomLane uses one typed safety core for control flow, effects, conflicts, resources, hashes, and authorization, then tailors execution to the active platform and workload. Its cross-process host scheduler evaluates each ready batch together, shares CPU and memory capacity across concurrent Codex tasks, and adapts to topology, load, thermal, power, and memory conditions. It delegates concurrency to native owners when safer, isolates Windows, WSL, and Docker realms, and executes exact verified plans with live progress and honestly labeled savings.",
    "developerName": "cloudguo123",
    "category": "Productivity",
    "capabilities": [
      "Local execution",
      "Parallel scheduling",
      "Cross-process host admission control",
      "Batch-level ready-set scheduling",
      "Dynamic CPU and memory capacity refresh",
      "Atomic workload compilation",
      "Typed effect analysis",
      "Plan hash verification",
      "In-task work discovery",
      "Visible per-prompt acceleration assessment",
      "Advisory lifecycle hook",
      "Native concurrency delegation",
      "Resource-bounded pytest-xdist worker pools",
      "Scenario profiling",
      "Trace-informed routing",
      "Workload-tailored execution",
      "Cross-platform safety core",
      "Resource awareness",
      "Windows Job Object process-tree control",
      "Windows ConPTY and UTF-8 pipe progress",
      "PowerShell file workflows",
      "Windows, WSL, and Docker realm isolation",
      "Apple silicon routing",
      "Python parallelism advice",
      "Source-hash-bound rewrite previews",
      "GIL-aware executor selection"
    ],
    "brandColor": "#65E6B4",
    "composerIcon": "./assets/growth/listing-logo.svg",
    "websiteURL": "https://cloudguo123.github.io/atomlane/",
    "privacyPolicyURL": "https://github.com/cloudguo123/atomlane/blob/main/PRIVACY.md",
    "termsOfServiceURL": "https://github.com/cloudguo123/atomlane/blob/main/TERMS.md",
    "logo": "./assets/growth/listing-logo.png",
    "screenshots": [
      "./assets/growth/social-preview.png"
    ],
    "defaultPrompt": [
      "Use $accelerate-local-work to run only the concurrency proven safe for this project.",
      "Use $optimize-python-parallelism to review this long-running Python entrypoint for a safe parallel refactor.",
      "Use $accelerate-local-work to run this independent pytest suite in one bounded native worker pool with live savings."
    ]
  },
  "mcpServers": "./.mcp.json"
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[atomlane on Agent Plugins Marketplace](https://pluginsmp.com/plugins/atomlane)