Augment review alternative with a direct requirement-check rate

Catch the fix an agent removes later.

A saved requirement makes a recurring mistake checkable. In this Perch capture from September 20, 2026, the same rule flags a missing guard and passes after the guard is restored.

def refund(order, payment):
    payment.refund(order.total)
    order.status = "refunded"
    return order

def refund(order, payment):
    if order.status == "refunded":
        return order
    payment.refund(order.total)
    order.status = "refunded"
    return order

Source: public order-service checkout.py at the linked commit. The captured standalone file is refund.py. Perch command output and timestamp. This saved-rule demonstration does not measure Augment Code Review's detection rate.

Perch vs Augment Code Review: what your team runs.

Perch turns project behavior into focused checks that agents can run before committing. Use these differences to choose the review workflow and billing model your team needs.

Augment review alternative with a direct requirement-check rate

Augment bundles coding and review in a flat subscription with metered usage. Choose Perch when you want a separately selectable semantic requirement with a direct fresh-check rate. The MIT CLI can run inside the agent's edit loop and in CI.

Review before committing

Augment Code Review: CLI access is included; GitHub AI review is a documented workflow. Augment Code Review workflow documentation.

Perch reads the current working file with perch check. For a known requirement, select its rule name and method instead of requesting another broad review. A local CLI describes where the command runs; Perch sends relevant source to hosted TypeSafe models for analysis.

How do saved requirements differ?

Augment Code Review: Project context guides review; precise custom-review rule limits were not verified. Augment Code Review rule documentation.

Perch stores English ensure rules in perch.yaml or .perch/rules/. Project, file and method scopes determine what is checked. Run the named check after an edit and after the repair; a rule finding can fail the command and a CI gate. Perch rules · Working-file checks.

What does the review bill depend on?

Compare Augment Code Review's billing unit and Perch's usage estimate

Is the CLI open source and offline?

Augment Code Review: Commercial coding and review service. Augment Code Review product or license source.

Perch’s CLI is MIT-licensed; hosted model inference is a separate paid service included in its published check rate. It does not run the model offline. Unchanged requests can reuse cached answers for free. Fresh judgments can vary, and a passing requirement check does not prove application correctness. Perch MIT license.

When does Augment Code Review fit the workflow?

Augment combines coding-agent access and GitHub review. Model cost, service fees, compute and top-ups can affect usage; the displayed subscription is not the guaranteed price of every review volume.

Estimate the review bill

Perch and Augment Code Review: pricing, allowances and workload calculator

Make the agent check its next edit.

npm install -g @lakeday/perch

perch rules add refund-once \
  --where refund.py --each method \
  --ensure "Refunded orders cannot be refunded again."

perch check refund.py::refund --rules refund-once

Use perch scan for repository code at Git HEAD and changed-code CI checks for pull requests. New model judgments can vary. Repeatability comes from cached answers for unchanged requests; a pass does not prove application correctness.