prpm-development

A knowledge base for developing PRPM, a package manager for sharing AI prompts, agents, and rules across coding tools. It covers package formats, conversion, dependencies, testing, quality standards, and deployment.

In plain words
What is it for?
Use it to develop PRPM features, define package formats, convert packages between tools such as Cursor and Claude Code, manage collections and dependencies, test quality, and prepare releases.
Why use it?
It helps keep packages portable between different AI editors while supporting versioning, reproducible installs, and dependency handling.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/pr-pm/prpm/prpm-development
Any agent
npx skills add pr-pm/prpm --skill prpm-development
Clone the repo
git clone --depth 1 https://github.com/pr-pm/prpm

Made for: Claude Code, Codex.

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,170 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00036 $0.07170
Opus 5 $0.00018 $0.03585
Sonnet 5 $0.00007 $0.01434
Haiku 4.5 $0.00004 $0.00717

Measured 2d ago against content hash 8bcde8d837c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prpm-development scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/prpm-development/SKILL.md · 901 lines

How it starts

The opening of the file, as written. The whole thing — 901 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PRPM Development Knowledge Base

Complete knowledge base for developing PRPM - the universal package manager for AI prompts, agents, and rules.

Mission

Build the npm/cargo/pip equivalent for AI development artifacts. Enable developers to discover, install, share, and manage prompts across Cursor, Claude Code, Continue, Windsurf, and future AI editors.

Core Architecture

Universal Format Philosophy

  1. Canonical Format: All packages stored in normalized JSON structure
  2. Smart Conversion: Server-side format conversion with quality scoring
  3. Zero Lock-In: Users convert between any format without data loss
  4. Format-Specific Optimization: IDE-specific variants (e.g., Claude with MCP)

Package Manager Best Practices

  • Semantic Versioning: Strict semver for all packages
  • Dependency Resolution: Smart conflict resolution like npm/cargo
  • Lock Files: Reproducible installs (prpm-lock.json)
  • Registry-First: All operations through central registry API
  • Caching: Redis caching for converted packages (1-hour TTL)

Developer Experience

  • One Command Install: prpm install @collection/nextjs-pro gets everything
  • Auto-Detection: Detect IDE from directory structure (.cursor/, .claude/)
  • Format Override: --as claude to force specific format
  • Telemetry Opt-Out: Privacy-first with easy opt-out
  • Beautiful CLI: Clear progress indicators and colored output

Git Workflow - CRITICAL RULES

⚠️ NEVER PUSH DIRECTLY TO MAIN ⚠️

PRPM uses a branch-based workflow with CI/CD automation. Direct pushes to main bypass all safety checks and can break production.

ALWAYS follow this workflow:

  1. Create a branch for your changes:

    git checkout -b feature/your-feature-name
    # or
    git checkout -b fix/bug-description
    
  2. Make commits on your branch using conventional commit format:

    git add [files]
    git commit -m "feat: add OpenCode format support"
    

Read the full file on GitHub · 901 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 901 lines · 36 tokens per session scan A 8bcde8d837c8

Subscribe to this mod's changes

prpm-development is a skill published in the GitHub repository pr-pm/prpm (120 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 7,170 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.