Perch checks the file on disk while the agent is still editing it. That is useful when the immediate task is preserving one requirement before the change is committed.

Check a saved rule on the current method

This is the same requirement and command used in the captured refund example:

- name: refund-once
  where: checkout.py
  each: method
  ensure: Refunded orders cannot be refunded again.

The deliberately broken method calls the payment provider without checking the order status:

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

Run the focused check from the repository root:

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

In the September 20, 2026 capture, the unguarded refund was flagged at 80% confidence and exited 3. Adding if order.status == "refunded": return order before the payment call made the check pass and exit 0. The capture uses refund.py; use checkout.py when adapting the public order-service source at commit 4af67af.

Save the rule with the code, then use the same command to check the next agent edit. Add regression tests for concurrency and payment-provider idempotency in the application.

Compare the review workflow

Workflow Perch Greptile
Immediate input Current working file with perch check Documented CLI branch review uses committed changes
Requirement format Named YAML rule with an English ensure Natural-language standards under .greptile/
Review scope One file or method, then changed-code CI scans Repository-aware branch and pull request review

Check working code before committing

Perch checks the method on disk while the agent is still editing. When an edit removes an access check or restores a previously fixed bug, run the saved rule immediately, repair the finding, and recheck before committing. The focused command makes the requirement part of the editing loop.

How Greptile handles review

Greptile documents graph-based codebase context, version-controlled custom standards, and a CLI review workflow. Its CLI documentation describes reviewing committed branch changes and ignoring uncommitted changes.

Add Perch to your agent workflow

Follow the Perch quick start, then save the requirement with the code. Install the skill for the coding agent you use:

perch setup claude-code
# Or: perch setup codex
# Or: perch setup cursor

The Perch skill instructs the agent to check the named rule after each relevant edit, inspect the finding, repair the code, and recheck. Keep the rule and regression test beside the application so the next session can use the same requirement.

With your base reference fetched, add perch scan --since origin/main --filter type=lint beside your tests in CI. CI setup explains the changed-code scan. Gated findings exit 3; exits 1 and 2 mean the check did not complete.

Compare cost and result limits

Perch charges 10¢ per 1,000 rule checks, with cached checks free. The pricing comparison estimates about 50¢ for a mid-sized pull request with about 150 methods read, including surrounding code. Usage follows the selected questions and their code context.

Unchanged requests reuse cached answers for free; fresh model judgments can vary. Perch’s CLI is MIT licensed. Model analysis sends relevant source to the configured service.

Competitor documentation reviewed October 14, 2026. All comparisons · Perch rule syntax