23 terminal tools.
One npm install.

The default command. Scans your Claude Code sessions for token consumption, cost breakdown, and cache hit rates.

Discovers 22+ configured services from your .env.local and queries each API in parallel. One command, your entire stack.

Pushes token stats, session data, and provider costs to your PromptReports.ai dashboard with delta-push checkpoints.

10 diagnostic checks: Node.js, .env.local, services, API key, Claude Code sessions, git, Prisma, CLAUDE.md, skills.

Wraps any shell command. Captures stdout/stderr, strips ANSI, collapses repeated lines, elides long stack traces, and truncates uniform blocks. Errors pass through. Exit code preserved.

Compares your local .env.local against Vercel production variables. Finds drift before it breaks prod.

Post-deploy health check. Production URL, Sentry errors, provider billing, Git status, DATABASE_URL. 0-100 score.

Exports env vars (AES-256 encrypted), skills, CLAUDE.md, LESSONS.md, MCP config, VS Code extensions into a single portable bundle.

Restores a setup-export bundle on a fresh machine: env vars, skills, CLAUDE.md, MCP config, VS Code config — one command.

Pulls unresolved issues from Sentry, deployments from Vercel, exceptions from PostHog into one time-sorted stream.

Searchable history of every Claude Code session with cost, turn count, model, content preview. Replay turn-by-turn.

Measures context window consumption: CLAUDE.md, skills, memory, system prompt. Finds skills that load but never get invoked.

Groups AI costs by model, git commit, or provider. Shows unit economics and cost anomalies.

Categorizes every turn by task type (search, read, write, complex) and suggests model downgrades. Opus is for architecture. Not grep.

Walks lib/ and app/api/ to find LLM call sites. Checks git history for modifications. Flags deprecated models.

Comprehensive audit of CLAUDE.md, .claude/ structure, skills, .env.local, settings.json, plans, memory. 0-100 score.

Deep token-budget analysis of your root CLAUDE.md. Detects duplicated phrases, oversized examples, dead file references, sections duplicating other docs, and filler words. Shows projected savings per session.

Extends context with a scanner for waste that never shows in summaries. Finds duplicate tool results across sessions, oversized tool payloads, post-compaction residue, and unused loaded skills. Reports waste + estimated monthly cost.

Kick off a multi-channel demand-gen campaign directly from the CLI — manual launches, npm-release triggers, and campaign inspection.

Finds stale API routes (180+ days), unused components, zombie dependencies. Delete with confidence.

Runs npm audit for CVEs, npm outdated, unused packages, license compliance. Every dependency, explained.

Parses prisma/schema.prisma, validates schema, checks migration status. Counts models, fields, relations.

Analyzes hotspot files, commit velocity, tech debt indicators, coding time patterns. Auto-generates changelogs.