apm: Agent Package Manager

by microsoft · Codex Skill · ★ 4.3k

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

Featured in: Skill & Agent Management

How to install apm

brew install microsoft/apm/apm
pip install apm-cli

Taken from the project's README on GitHub. Check the security audit before running it.

Security audit verdict: SAFE · quality 60/100

None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.

🧪 Tested by Agent Skills Hub

One of 14 tools we ran end to end on the same task for our Skill & Agent Management page (2026-10-09).

Our pick (If a team wants a manifest and a lockfile): A package manager: skills are declared in a file, installed and removed exactly. It rejected skills with invalid frontmatter. It gives no warning about scripts, so read a skill before adding it.

Result: Installed a skill with a curl | sh script, showing only its source · removes skills cleanly · syncs to Codex · +345 tokens per session for 20 skills

See the run → · See the whole test →

ai-agentsclaude-codecodex-clicontext-engineeringgithub-copilotpackage-managerprompt-engineering

Quick Facts

Stars4,258
Forks416
LanguagePython
CategoryCodex Skill
LicenseMIT
Quality Score60/100
Open Issues298
Last Updated2026-11-06
Created2025-09-18
Platformsclaude-code, cli, codex, node, python, rust
Est. Tokens~14k

About apm

APM – Agent Package Manager An open-source, community-driven dependency manager for AI agents. Think , , or — but for AI agent configuration. GitHub Copilot · Claude Code Documentation · Quick Start · CLI Reference Why APM AI coding agents need context to be useful — standards, prompts, skills, plugins — but today every developer sets this up manually. Nothing is portable nor reproducible.

Compatible Skills

These tools work well together with apm for enhanced workflows:

  • mcpm.sh — semantic(0.37)+complementary+rare_topics+same_lang+similar_pop+shared_platform (63%)
  • agent-resources — semantic(0.47)+complementary+same_lang+similar_pop+shared_platform (61%)
  • craftdesk — semantic(0.47)+complementary+rare_topics+similar_pop+shared_platform (56%)
  • kindly-web-search-mcp-server — semantic(0.16)+complementary+same_lang+similar_pop+shared_platform (56%)

apm alternative? Top 6 similar tools

Looking for a apm alternative? If you're comparing apm with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • claude-scholar by Galaxy-Dawn · ⭐ 5.8k

    Semi-automated research assistant for academic research and software development. Supports Claude Code, Codex

  • ralph-orchestrator by mikeyobrien · ⭐ 3.2k

    An improved implementation of the Ralph Wiggum technique for autonomous AI agent orchestration

  • vibe-coding-prompt-template by KhazP · ⭐ 3.1k

    Templates and workflow for generating PRDs, Tech Designs, and MVP and more using LLMs for AI IDEs

  • pro-workflow by rohitg00 · ⭐ 2.9k

    Claude Code learns from your corrections: self-correcting memory that compounds over 50+ sessions. Context eng

  • ai-devkit by codeaholicguy · ⭐ 1.7k

    The control plane for AI coding agents.

  • cccc by ChesterRa · ⭐ 1.3k

    Coordinate your coding agents like a group chat — read receipts, delivery tracking, and remote ops from your p

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Python Agent Tools

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Codex Skill tools