AI assistants and search decision
ClaudeKit
Build: a competent engineer can recreate a single ClaudeKit kit and the ck CLI in about 40 hours and run it locally; pay for the product if you want the full curated catalogue, continuous updates, and vendor convenience.
Visit website↗$14.99/mo
$180/yr
Read off the official pricing page.
$100one-off40 h to build
$0/mo2 h/mo upkeep
On cash alone, building overtakes the subscription at 1 seat.
Open-source builds that already do this
Every project below is open source and already does this job today. Fork one, self-host it, or take the parts you need - the build prompt further down assumes an empty file, and this is the shortcut past that. Licences differ; check the one on each card before you ship. All ClaudeKit alternatives, with the arithmetic →
What a replacement has to do
- Provide a ck CLI that installs a kit (files of slash commands, skills, and read-only agents) into a user's Claude Code environment and ships a manifest.json that lists per-file token costs; users invoke namespaced slash commands inside Claude Code to run end-to-end workflows.
What it still won’t have
- The curated set of 100+ ready-made commands, skills, and subagents across six kits as shipped
- The public, versioned manifest token ledger and the convenience of instant CLI delivery for all kits and future kits
- Priority support and continuous tuned updates delivered via subscription
What remains hard
- Product polish and ongoing maintenance
First-year cost
Keep paying
Paying is—cheaper in year one.
On cash alone, building overtakes the subscription at 1 seat.
Money you would actually spend
Time you would spend
—
What you would spend
What we assumed
The verdict above measures whether you could build it. This one is only about money.
Runnable build prompt
Build a ClaudeKit-compatible ck CLI and a single-kit packer using Node.js (ESM) and GitHub Actions for releases. Scope: implement ck install <kit> that writes a kit folder of slash command files, SKILL.md files, and read-only agent files into a target Claude Code plugins directory; implement a pack script that computes a per-file token cost heuristic and writes manifest.json; implement ck tokens <kit>, ck list, license activation via a simple license key file, and 10 example slash commands (including one flagship command) that return structured evidence (JSON table or before/after diff). Out of scope: training or hosting LLMs, model tuning, or commercial licensing server. Require: input validation, idempotent install/uninstall, error handling, unit tests for CLI commands, and CI that publishes a versioned tarball and manifest.
How we checked
How the score was reached
- Build verdict base78
- An open-source build was found+5
- 4 cited sources+3
- Price verified on pricing page+3
- 3/3 assessment runs agreed+4
- Evidence score93
The base comes from the verdict. Everything under it is a check that either happened or did not, and each one is a fact frozen in this record rather than a judgement made at render time - so the same evidence always produces the same number.
How scoring works →Cited sources · 4
Every page the run actually retrieved.
- official productClaudeKit official product
- official pricingClaudeKit pricing
- official docsClaudeKit docs
- open sourceOthmanAdi/planning-with-files
Integrity checks
What held up, and what did not.
