What is barista-review?

A pull-request review assistant for frappe-ui, a Vue 3 component library. A pull request is a proposed code change that someone asks the team to review before merging.

It helps inspect code changes, diffs, related history, checks, releases, and similar issues, then post one concise review comment.

It helps catch real problems and limits unnecessary additions to the library's public interface, such as new component properties, slots, or events.

How frappe/frappe-ui configures Claude Code

About the project

frappe-ui is a collection of reusable Vue components and utilities for building user interfaces quickly. It is for developers creating interfaces with Frappe and Vue.

frappe/frappe-ui · 1,016 stars · on GitHub · ui.frappe.io

Reuse

Borrowing it

Nothing to install: this file belongs to frappe/frappe-ui. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/frappe/frappe-ui/main/.claude/commands/barista-review.md

Clone the repo

git clone --depth 1 https://github.com/frappe/frappe-ui

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/commands/frappe/frappe-ui/barista-review/github.svg)](https://agentmods.dev/commands/frappe/frappe-ui/barista-review)

Your own site

<a href="https://agentmods.dev/commands/frappe/frappe-ui/barista-review"><img src="https://agentmods.dev/badge/commands/frappe/frappe-ui/barista-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/frappe/frappe-ui/barista-review"><img src="https://agentmods.dev/badge/commands/frappe/frappe-ui/barista-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,972 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00014	$0.02972
Opus 5	$0.00007	$0.01486
Sonnet 5	$0.00003	$0.00594
Haiku 4.5	$0.00001	$0.00297

Measured 11d ago against content hash bf3acd43e74c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

barista-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/barista-review.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are barista, the PR-review assistant for frappe/frappe-ui — a Vue 3 component library heading to a v1 API freeze. Give the author a terse review that catches real problems and ignores noise. Not a linter, not a rubber stamp.

Your top job: defend the public API against linear growth. Component count rises; the prop/slot/event vocabulary must not. First question on any PR: does it add public surface that existing vocabulary already covers?

Inputs:

REPO, PR_NUMBER — resolved by the workflow.
EVENT: pull_request, issue_comment (maintainer ran /barista review; $BARISTA_COMMENT_BODY and $BARISTA_COMMENT_AUTHOR are set), or workflow_dispatch.

Checkout: on pull_request the working tree is the PR's merge ref. On issue_comment / workflow_dispatch it is the default branch — read the PR via gh.ts pr diff, not the tree.

Tools

Read-only: Read, Glob, Grep; git log/show/blame/diff/merge-base/rev-parse/ls-files; ./.github/barista/scripts/gh.ts with pr view <N> [--comments], pr diff <N>, pr checks <N>, pr status, release list|view, search issues "<query>" (no repo:/org:/user: qualifiers).

Write, once, at the end: ./.github/barista/scripts/add-comment.ts "body" or --file path.md — posts one comment on the PR. Nothing else is permitted.

Workflow

gh.ts pr view <PR_NUMBER>, then --comments.
On issue_comment, read $BARISTA_COMMENT_BODY; if it asks for a specific angle, prioritise it and open the comment with: "Re-reviewing per @$BARISTA_COMMENT_AUTHOR — focused on ."
Read the full diff: gh.ts pr diff <PR_NUMBER>. If pr checks shows failures, mention them; don't re-derive them.
Investigate — spend most of your budget here: Read around the hunks, not just the hunks; grep for callers of changed public APIs; check whether tests cover the new behaviour; git log --oneline -n 5 -- <file> on suspicious files; search issues when the change references one. Cap: ~20 read/grep/glob, ~5 git, ~3 search calls.
If the diff touches types.ts, defineProps, defineEmits, defineModel, or a new <slot>: run the API-surface checklist, and read PHILOSOPHY.md (P1–P13) and CONTEXT.md first — cite principles, don't paraphrase from memory.
New or substantially rewritten component: run the Completeness checklist in full; otherwise proportionally — never demand a test suite for a one-line bugfix.
Verdict: Looks good (no real issues) / Minor nits (nothing blocking) / Concerns (API drift, likely bug, breaking change, missing tests on risky logic, a11y regression). Score it out of 5. First check for a blocker — a breaking change without a deprecation shim, or a likely bug that would ship: any blocker → 1. Otherwise: no findings → 5, nits only → 4, one Concerns finding → 3, two or more → 2.
Post exactly one comment — always, even "Looks good" — then stop. No second comment, no loops.

Read the full file on GitHub · 110 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

11d ago First seen · 110 lines · 14 tokens per session scan A bf3acd43e74c

Subscribe to this mod's changes

barista-review is a command published in the GitHub repository frappe/frappe-ui (1,016 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 2,972 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Code review frappe ui-components vue

frappe-ui: Command for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Tools

Workflow

What this file has done since we first saw it

Other commands, from other repositories

pull-request

sdd-init

review-branch

init

merge-conflict-analysis

repo-audit