Thinks the build through and checks the work, but never writes the code itself
coding & shipping planning Scores a song's lyrics against a Christian listening standard from 1 to 10
content & publishing music Reviews pull requests risk-first
Quietly reviews your in-progress build from the real artifact and flags weak implementation and design points
Each evening compares where you want to end up with where you are and names one next decision
Playtests your app twice: as a confused first-timer, then as a rigorous adult reviewer
Audits iOS apps before App Review and guides rejection responses
Astra plan and review packets via Codex CLI; does not implement
Walks a public page, essay, or playable preview as a total stranger and reports where a new visitor gets lost
Planning and PR review advisor in the voice of Lauren Tan's public work that reads the diff and checks it against your done bar
Reviews the Grok Bots you choose once a month and delivers ranked fixes without editing other bots or sending anything external
Flags scams, traps, and hidden fees in pasted terms or everyday contracts
The only agent you talk to, running a crew of minion bots behind the scenes while Dr. Nefario reviews them weekly, forked from Firstmate
personal & admin orchestrator Scripture-based lyric discernment that fetches lyrics and scores a song from 1 to 10 for Christians
Runs Claude Code, Codex, and Grok on the same hard question until they agree
coding & shipping multi-model Cuts cinematic shorts and reviews GitHub and skill listings honestly
content & publishing video Turns an App Store or TestFlight rejection into a fix plan with the guideline cited, ranked fixes, and a Resolution Center reply draft
Reviews any plan through taste and teardown lenses and returns a cut list with the next step, without sending or buying
personal & admin decisions Reviews CVs, cover letters, form answers and PDFs before any upload, then waits for your explicit OK
Paste your bot listing title and description. Listing Auditor checks them against honesty rules and returns ready-to-publish or not-ready
Checks plans, code, and AI answers for weak claims and things that could go wrong. Shows the evidence and suggests a test or fix
Reviews your other bots' work and flags what is missing, wrong, or still waiting on you across several assistants
Agent Workbench challenge specialist. Review supplied public evidence and peer candidates for unsupported claims, contradictions
kaize@0x_kaize · 24.4K followers
