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

tokrepo

v3.23.5

Published

Agent-native CLI for discovering, verifying, installing, and publishing reusable AI skills, prompts, MCP configs, scripts, and workflows.

Vulnerabilities

Powered byPowered by Snyk
  • 0High
  • 0Medium
  • 0Low

Links

Git

Maintainers

keeprulekeeprule

Keywords

aipromptskillworkflowmcptokrepoclaudecodexcursorgeminicopilotclinewindsurfopenhandsaideragentagent-toolsagent-skillsclaude-codeopenai-codexmcp-registryhosted-mcpagent-manifesta2a-agent-cardllms-txttrust-verificationcapability-resolutionasset-harvestagent-auditagent-evals

Readme

TokRepo CLI

Agent-native CLI for discovering, installing, and publishing reusable AI assets: skills, prompts, MCP configs, scripts, workflows, and project instructions.

Agent Bootstrap

Run this once in any repository that will be touched by coding agents:

npx -y tokrepo@latest init-agent --target all

It writes a managed TokRepo block into the project memory files that agents already read: AGENTS.md, CLAUDE.md, GEMINI.md, .cursor/rules/tokrepo.mdc, .github/copilot-instructions.md, .github/instructions/tokrepo.instructions.md, .clinerules/tokrepo.md, .windsurf/rules/tokrepo.md, .roo/rules/tokrepo.md, .openhands/microagents/repo.md, CONVENTIONS.md, .mcp.json, and .tokrepo/agent.json. Future agents get a local rule to call tokrepo_resolve_capability or tokrepo_discover during planning instead of inventing a one-off local helper first.

Planning-Time Discovery

For agents without MCP access:

npx -y tokrepo@latest agent-check "audit this Nuxt app for SEO gaps" --json
npx -y tokrepo@latest resolve "audit this Nuxt app for SEO gaps" --target codex --json

For MCP clients:

npx -y tokrepo-mcp-server

Then call tokrepo_resolve_capability, inspect with tokrepo_detail, call tokrepo_verify for hashes, permission envelope, policy, trust_score_v2, evidence_bundle, SBOM-lite, and signature_evidence, call tokrepo_install_plan before writing files or activating assets, and use lifecycle tools for installed state, update, uninstall, and rollback.

Successful installs write project-local lifecycle state to TokRepo.lock and .tokrepo/state.json. Agents should inspect it with:

npx -y tokrepo@latest installed --project --json

Post-Task Handoff

After an agent creates reusable instructions, scripts, prompts, or configs:

npx -y tokrepo@latest agent-handoff --json
npx -y tokrepo@latest harvest --changed --json

MCP clients can call tokrepo_harvest for private-by-default package drafts or tokrepo_handoff_plan for the legacy read-only packaging plan. These flows expose quality_gate, package_manifest, SBOM-lite, and provenance, only suggest private tokrepo push commands, and never publish automatically.

Common Commands

tokrepo search "code review skill" --kind skill --policy allow --json
tokrepo resolve "code review skill" --target codex --json
tokrepo detail <uuid> --json
tokrepo verify <uuid> --target codex --json
tokrepo plan <uuid> --target codex
tokrepo install <uuid> --target codex --dry-run --json
tokrepo installed --project --json
tokrepo installed --target codex --json
tokrepo sync-installed --target codex --dry-run --json
tokrepo uninstall <uuid> --target codex --dry-run --json
tokrepo rollback --last --target codex --dry-run --json
tokrepo harvest --changed --json
tokrepo push . --private --kind skill --target codex --install-mode bundle

Machine-Readable Discovery

  • Manifest: https://tokrepo.com/.well-known/tokrepo.json
  • MCP server manifest: https://tokrepo.com/.well-known/mcp/server.json
  • Portable agent manifest: https://tokrepo.com/.well-known/agent.json
  • A2A agent card: https://tokrepo.com/.well-known/agent-card.json
  • Tool catalog: https://tokrepo.com/.well-known/tool-catalog.json
  • Trust manifest: https://tokrepo.com/.well-known/tokrepo-trust.json
  • Default agent policy pack: https://tokrepo.com/policy-packs/default-agent-policy.json
  • Agent baseline eval: https://tokrepo.com/evals/agent-baseline.json
  • Eval evidence: https://tokrepo.com/evals/agent-discovery.json
  • Multi-agent compatibility: https://tokrepo.com/evals/multi-agent-compatibility.json
  • Agent memory schema: https://tokrepo.com/schemas/agent-memory.schema.json
  • Agent evidence bundle schema: https://tokrepo.com/schemas/agent-evidence-bundle.schema.json
  • Capability resolution schema: https://tokrepo.com/schemas/capability-resolution.schema.json
  • Harvest report schema: https://tokrepo.com/schemas/harvest-report.schema.json
  • Handoff package schema: https://tokrepo.com/schemas/handoff-package.schema.json
  • Agent instructions: https://tokrepo.com/agent-instructions/tokrepo.md
  • Agent text entry: https://tokrepo.com/agents.txt
  • Agent ecosystem distribution pack: https://tokrepo.com/agent-ecosystem.json
  • LLM crawler entry: https://tokrepo.com/llms.txt

Use https://tokrepo.com/agent-ecosystem.json when adding TokRepo to starter templates, README files, install guides, example projects, agent tool marketplaces, or registry submission forms. It contains the canonical agent_marketplace_listing copy, ecosystem_channels, target project-memory files, and verification commands.

TokRepo records anonymous aggregate funnel events for capability resolution, discovery, verify, plan, install, harvest, handoff, and push. It does not send task text or file contents. Disable with TOKREPO_TELEMETRY=0.