JSPM – tracerkit@1.5.0

Package Exports

tracerkit

Readme

Replace ad-hoc AI prompts with a repeatable spec-driven workflow: from idea to verified, archived code.

Named after the tracer-bullet technique from The Pragmatic Programmer — Tracer + Kit.

Zero runtime dependencies. Pure Markdown skills, no build step.

Why TracerKit?

Without specs, every AI session starts from scratch — vague prompts, duplicated context, no way to confirm "done." Most planning tools produce flat task lists where nothing works until everything is done.

TracerKit takes a different approach: tracer-bullet vertical slices. Each phase cuts through every layer (schema → service → API → UI → tests), so every phase is demoable on its own. Integration problems surface early, context stays focused, and AI assistants get small, well-scoped phases instead of sprawling layers.

Get Started

Install

npx tracerkit init

Skills are installed globally to ~/.claude/skills/, available in every project. No per-project setup needed.

Workflow

You: /tk:prd add dark mode support
AI:  ✓ Written .tracerkit/prds/dark-mode-support.md

You: /tk:plan dark-mode-support
AI:  ✓ Phase 1 — CSS variables + ThemeProvider
     ✓ Phase 2 — Toggle component + localStorage
     ✓ Written .tracerkit/plans/dark-mode-support.md

You: # implement each phase...

You: /tk:check dark-mode-support
AI:  ✓ All checks verified — status: done
     Archived to .tracerkit/archives/dark-mode-support/

See Examples for full walkthroughs.

Per-project usage

To scope skills to a single project (team members get them via git):

npx tracerkit init .              # install to .claude/skills/ in current dir
npx tracerkit update .            # update project-scoped skills
npx tracerkit uninstall .         # remove project-scoped skills

Skills

TracerKit ships three skills that take a feature from idea to verified archive.

`/tk:prd <idea>`: Write a PRD

Interactive interview that explores your codebase, asks scoping questions one at a time, designs deep modules, and writes a structured PRD.

Output: .tracerkit/prds/<slug>.md

`/tk:plan <slug>`: Create an implementation plan

Reads a PRD and breaks it into phased tracer-bullet vertical slices. Each phase is a thin but complete path through every layer (schema, service, API, UI, tests), demoable on its own.

Output: .tracerkit/plans/<slug>.md

`/tk:check [slug]`: Check and archive

Checks the codebase against the plan's done-when checkboxes. Runs tests, validates user stories, updates check progress, and transitions the PRD status. On done, archives the PRD and plan to .tracerkit/archives/<slug>/ automatically.

Without arguments, shows a feature dashboard with status and progress before asking which feature to check.

Output: Verdict block in .tracerkit/plans/<slug>.md. On done: .tracerkit/archives/<slug>/prd.md + .tracerkit/archives/<slug>/plan.md

Docs

Document	Description
Examples	Walk through end-to-end usage scenarios
CLI Reference	Browse all CLI commands and flags
Configuration	Configure custom artifact paths via `config.json`
Metadata Lifecycle	Understand YAML frontmatter states and transitions
Compared to	Compare TracerKit to Spec Kit, Kiro, and OpenSpec

Contributing

Fork the repo and create a feature branch
Use TracerKit itself to plan your change (/tk:prd + /tk:plan)
Implement following the plan phases
npm run lint:fix && npm run test:run && npm run typecheck
Conventional Commits (enforced by commitlint)
Open a PR against main

Support

For support, please open a GitHub issue. We welcome bug reports, feature requests, and questions.

Acknowledgments

This project was born out of Claude Code for Real Engineers, a cohort by Matt Pocock. The hands-on approach to building real things with Claude Code sparked the idea for TracerKit. If you're serious about AI-assisted engineering, I can't recommend Matt's cohorts and content highly enough.

tracerkit