Not every ship should clear the runway unseen.
Review · Route · Repair · Verify
Occasional notes on how we think about PR review, policy, and safer merges — plus product updates when they ship. No spam; unsubscribe any time.
Stay in the loop
Prefer the full waitlist? Create an account.
Search paths
Prefer a page with more depth before you subscribe?
These are the public resources that earn the most search traffic and answer the main follow-up questions around AI code review, pricing, comparisons, and model choice.
Harness
Critique Code
Agentic coding harness, same class as Codex. TTY or critique-code web on 127.0.0.1. Binary critique-code from @critiquedotsh/harness. Trial on Verify.
Install
Install Critique CLI
npm install --global @critiquedotsh/cli — local working-tree finish pass for coding agents.
Author
CritiqueCode harness
npm install --global @critiquedotsh/harness — author agent (critique-code). Same org as the sidecar CLI, not a rename of it.
Author
What's new in CritiqueCode
0.1.3 vs 0.1.0: login, critique/auto, voice, skills, workers, and critique-code web. Forced review did not move.
Author
CritiqueCode web UI
critique-code web: local browser on 127.0.0.1, same forced-review author kernel.
Docs
Critique CLI documentation
finish.v1 contract, repair modes, integrate for Codex, Claude Code, OpenCode, and Cursor.
Alternatives
Best CodeRabbit alternatives (2026)
Ranked shortlist: Critique CLI finish pass vs PR comment bots and implementation agents.
Compare
Critique CLI vs competitors
Head-to-heads vs CodeRabbit, Greptile, Copilot review, Bugbot, Codex, Claude Code, Devin.
vs CodeRabbit
Critique CLI vs CodeRabbit
Pre-commit finish.v1 evidence vs seat-priced PR comments — different moment in the loop.
vs Claude Code
Independent finish pass for Claude Code
Claude Code writes the change; Critique checks it with structured exit codes.
vs Codex
Critique CLI vs OpenAI Codex
Complementary: Codex implements, Critique finishes — not same-family self-grade.
Pricing
Critique CLI pricing
Shared credits (Solo $19 · Pro $49 · Team $149), student/OSS lane, BYOK harness.
Agents
Machine-readable pricing.md
Parseable plan table for AI shopping agents — no JavaScript wall.
Category
Best coding agent verification tools 2026
Category guide for independent finish passes vs CI and PR bots.
Essay
Critique vs built-in agent checks
Why an independent finish pass differs from an agent grading its own homework.
Essay
Your coding agent is lying to you
“Looks complete” is not verified — when to call a second opinion.
llms.txt
AI context file
Canonical product description, install workflow, and citation URLs for answer engines.
Essays
Blog and ship log
Product notes, buyer guides, and release updates.