Metabob comparison for repeatable behavior requirements

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 Metabob's detection rate.

Perch vs Metabob: 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.

Metabob comparison for repeatable behavior requirements

Turn a reviewed issue into a saved behavior requirement. Perch applies that rule directly to selected working files or methods, so the agent can check the fix before committing. The same English rule remains available after the chat session ends.

Review before committing

Metabob: MCP exposes issue-priority and codebase-search tools; standalone CLI was not verified. Metabob 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?

Metabob: Custom agents on Pro; a saved semantic-rule format was not verified. Metabob 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 Metabob's billing unit and Perch's usage estimate

Is the CLI open source and offline?

Metabob: Commercial analysis platform. Metabob 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 Metabob fit the workflow?

Metabob exposes agent tools for issue priority and codebase search as well as review. Full-repository analysis and local working-tree checks are separate scope questions; a standalone CLI was not verified.

Estimate the review bill

Perch and Metabob: 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.