npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@tracepact/cli

v0.5.0

Published

CLI for TracePact — interactive setup, model catalog, test runner

Downloads

764

Readme

@tracepact/cli

Command-line interface for TracePact — run tests, scaffold projects, audit skills, manage cache, and more.

Installation

npm install -g @tracepact/cli

# Or use via npx
npx tracepact

Commands

tracepact / tracepact run

Run TracePact tests via Vitest.

tracepact                          # Run tests in mock mode
tracepact --live                   # Run against real LLMs
tracepact --live --budget 50000    # Enforce token budget
tracepact --record                 # Record cassettes (implies --live)
tracepact --replay ./cassettes     # Replay from cassettes
tracepact --json                   # Output JSON results
tracepact --provider anthropic     # Use specific provider
tracepact -- --grep "security"     # Pass args through to Vitest

| Flag | Description | |------|-------------| | --live | Run against real LLM APIs | | --full | Include expensive tests (Tier 3-4) | | --record | Record cassettes from live runs | | --replay <dir> | Replay from recorded cassettes | | --no-cache | Skip response cache | | --budget <tokens> | Abort if token usage exceeds threshold | | --json | Enable JSON reporter | | --provider <name> | Select provider (openai, anthropic, etc.) | | --health-check-strict | Exit if provider health check fails |

tracepact init

Interactive setup wizard for new projects.

tracepact init                     # Interactive wizard
tracepact init --demo              # Self-contained demo (no API keys)
tracepact init --system-prompt     # Raw system prompt template
tracepact init --skill SKILL.md    # Generate from existing skill
tracepact init --pattern api-client  # Use a pattern template
tracepact init --force             # Overwrite existing files

Creates tracepact.config.ts, tracepact.vitest.ts, and a test file template. The interactive wizard walks you through provider, model, and judge selection.

tracepact audit

Static analysis of a SKILL.md file (no API key needed).

tracepact audit SKILL.md
tracepact audit SKILL.md --format json
tracepact audit SKILL.md --fail-on high   # Exit 1 if high+ severity found

Checks for:

  • Risky tool combinations (e.g. bash + network)
  • Prompt hygiene issues
  • Skill completeness
  • Opaque tool definitions

tracepact capture

Auto-generate a test file from a live run or recorded cassette.

tracepact capture --skill SKILL.md --prompt "Review this code"
tracepact capture --skill SKILL.md --prompt "test" --cassette ./cassettes/run.json --dry-run
tracepact capture --skill SKILL.md --prompt "test" --out tests/generated.tracepact.ts
tracepact capture --skill SKILL.md --prompt "test" --with-semantic

tracepact cache

Manage the response cache.

tracepact cache list               # Show cached entries
tracepact cache clear              # Delete all cache
tracepact cache clear --stale      # Delete only expired entries
tracepact cache verify             # Check cache integrity

tracepact models

Browse the model catalog.

tracepact models                   # List all providers and models
tracepact models openai            # Show only OpenAI models
tracepact models --verbose         # Include pricing details
tracepact models --refresh         # Force refresh from models.dev

Shows API key status, context window, and pricing per model.

tracepact cost-report

Show token usage from the last test run.

tracepact cost-report

Displays total tokens, API calls vs cache hits, per-provider and per-test breakdowns. Reads from .tracepact/last-run-tokens.json.

tracepact doctor

Environment and configuration health check.

tracepact doctor

Checks:

  • Node.js version (>=20)
  • Vitest installation
  • Config file presence (tracepact.config.ts)
  • SKILL.md existence
  • API keys for all known providers
  • Docker/Podman runtime availability
  • Cache directory writability

Environment Variables

| Variable | Description | |----------|-------------| | TRACEPACT_LIVE | Enable live LLM calls (1 to enable) | | TRACEPACT_FULL | Enable expensive tests (1 to enable) | | TRACEPACT_PROVIDER | Default provider name | | TRACEPACT_BUDGET | Max token budget | | TRACEPACT_RECORD | Enable cassette recording | | TRACEPACT_REPLAY | Path to cassette directory for replay | | TRACEPACT_NO_CACHE | Disable response caching |

License

MIT