Macroscope CLI freezes work in progress and meters hosted analysis through Agent credits. Cubic provides local review and Team custom agents with reviewed-line allowances. Both handle uncommitted work; compare the review unit and the recurring workload.
| Decision | Macroscope | Cubic |
|---|---|---|
| Review scope | GitHub reviews and local or agent-driven checks. | PR and local review with plan-specific reviewed-line allowances. |
| Local review input | MIT local CLI reviews working-tree and branch changes. | cubic review checks uncommitted edits or changes against a base branch. |
| Custom requirements | Markdown agent instructions, path selection and configurable check-run agents. | cubic.yaml custom agents; Team includes 5 agents. |
| License and service | MIT local CLI; commercial hosted analysis. | Commercial review service. |
| Official references | Macroscope sources | Cubic sources |
Use the same branch base, exclusions and saved requirement. Record Macroscope CLI analysis usage and Cubic reviewed lines and agent count. GitHub per-KB rates are not a quote for Macroscope CLI review.
GitHub Balanced review: 5¢/KB with a 10 KB minimum. Other modes: 2.5–20¢/KB. No seat fees.
GitHub diff-size pricing is separate from CLI/agent model cost plus 5%. Free monthly credits and welcome credit are available. No fixed per-PR total is assumed.
Team: $30/developer/month billed yearly. Starter includes 20 PR reviews/month free.
Team annual subscription floor, including 40,000 reviewed lines per seat per period; extra lines cost $20/10,000. Flex usage settings affect whether reviews pause.
Subscription amounts are plan floors or quoted allowances. Repeated reviews, selected effort, provider charges and exclusions can change the bill. Equal review counts do not establish equal analysis scope.
A third option for the agent’s next edit
Perch is a stronger fit when a specific behavior requirement needs an independent check. The agent can rerun that rule after fixing the method, with unchanged checks reused free.
For an agent that repeatedly removes tenant authorization from a database update, save the requirement as a named Perch rule:
- name: tenant-scoped-update
where: "orders.py"
ensure: >-
The cancellation UPDATE must constrain tenant_id to actor.tenant_id
before changing the order. An id-only or owner-only update breaks
this requirement.This requirement comes from the FastAPI tenant-authorization recipe, which includes the implementation, deliberate regression and captured Perch checks. The same named check can run against the working file after the next agent edit. Perch working-file checks support selecting rules directly; rule selectors cover project, file and method scope.
npm install -g @lakeday/perch
perch login
perch setup claude-code
# Or choose: perch setup codex
# Or choose: perch setup cursorUse the setup command for your coding agent. Download the focused pack without replacing existing files:
curl -fL 'https://reporules.fyi/fastapi/tenant-cancellation/rule-pack.zip' -o tenant-rule.zip
unzip -n tenant-rule.zip
perch check orders.py --rules tenant-scoped-update --json
# Repair the reported finding after the agent edit.
perch check orders.py --rules tenant-scoped-update --jsonKeep your existing root perch.yaml. The ZIP adds its focused rule under .perch/rules/; unzip -n preserves existing files. Review and adapt the selector and application path before running it in your repository. Run the saved check after an edit, repair any finding, and repeat the identical check alongside application regression tests.
Download the tenant-authorization rule pack · Inspect pack contents and agent task
Perch charges 10¢ per 1,000 fresh rule checks, with no developer seat fees. Cached unchanged checks are free. About 50¢ per mid-sized PR is a rounded estimate for approximately 150 methods read at the captured September–October 2026 density of 34 questions per method; the unrounded example is 51¢. A single named-rule check is a different scope. Team workload calculations show the assumptions.
The Perch CLI is MIT licensed; hosted analysis is paid and relevant source is sent to the configured model service. Fresh model judgments can vary. Unchanged requests can reuse cached results.
This article compares documented product workflows and terms. The public evaluation materials include captured Perch requirement checks; authenticated CodeRabbit and Greptile runs remain unscored. They do not establish a measured accuracy ranking between these tools.
Reviewed October 14, 2026. Unverified features are marked as unverified rather than treated as absent. Current terms and actual trial results should determine a purchase.