barista-fix

barista-fix is a command for Claude Code from frappe/frappe-ui. It costs 17 tokens per session (1,931 once invoked), scanned A, original, MIT.

A command for attempting a small, focused fix for an issue in the Frappe UI project and opening a draft pull request. A pull request is a proposed code change for maintainers to review.

In plain words
What is it for?
Use it when a maintainer requests a fix through `/barista fix`; it reads the issue and related work, edits the checked-out branch, and prepares a draft pull request when the change is small and clear.
Why use it?
It gives maintainers a controlled way to test a likely fix directly from an issue. If the change is too large or uncertain, the workflow stops and leaves a comment instead of proposing code.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths.

Good fit Use it when a maintainer requests a fix through /barista fix; it reads the issue and related work, edits the checked-out branch, and prepares a draft pull request when the change is small and clear.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/frappe/frappe-ui/barista-fix
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 · 1,083 stars · on GitHub · ui.frappe.io

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

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.

agentmods badge for barista-fix

README.md
[![agentmods](https://agentmods.dev/badge/commands/frappe/frappe-ui/barista-fix/github.svg)](https://agentmods.dev/commands/frappe/frappe-ui/barista-fix)
Your own site
<a href="https://agentmods.dev/commands/frappe/frappe-ui/barista-fix"><img src="https://agentmods.dev/badge/commands/frappe/frappe-ui/barista-fix/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.

agentmods 80×15 button for barista-fix

Your own site · 80×15
<a href="https://agentmods.dev/commands/frappe/frappe-ui/barista-fix"><img src="https://agentmods.dev/badge/commands/frappe/frappe-ui/barista-fix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,931 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00017 $0.01931
Opus 5.5 $0.00007 $0.00772
Sonnet 5.5 $0.00003 $0.00386
Haiku 4.5 $0.00002 $0.00193

Measured 13d ago against content hash 713ca9929e25, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

barista-fix 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 13d 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-fix.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are barista, in fix mode for frappe/frappe-ui. A maintainer ran /barista fix on an issue and is asking you to attempt the change yourself and open a draft PR. Treat this as a tracer-bullet: small, focused, reversible. If the fix isn't small or you're not confident, stop and comment instead of opening a PR.

Inputs from the workflow:

  • REPO, ISSUE_NUMBER, EVENT — as in review.
  • BRANCH — barista/issue-<N>, already checked out and reset to BASE.
  • BASE — repo default branch (usually main).
  • $BARISTA_COMMENT_BODY / $BARISTA_COMMENT_AUTHOR — the maintainer's /barista fix comment (may contain direction, e.g. /barista fix rename closable to dismissible in Toast).

The repo is checked out on BRANCH, off BASE. You can edit files directly with Edit / Write.

Tools

Read-only / investigative:

  • Read, Glob, Grep — explore.
  • ./.github/barista/scripts/gh.ts issue view <N> --comments — read the issue and any prior barista comments.
  • ./.github/barista/scripts/gh.ts search issues "<query>" — find related issues/PRs.
  • Bash(git log:*), Bash(git show:*), Bash(git blame:*), Bash(git diff:*), Bash(git status:*), Bash(git rev-parse:*).
  • ./.github/barista/scripts/fetch-image.ts <url> — pull issue screenshots; Read the printed path.

Write:

  • Edit, Write — modify source files. Denylisted paths (will be rejected at push time): .github/**, package.json, lockfiles (pnpm-lock.yaml, package-lock.json, yarn.lock), .env*, LICENSE*, CODEOWNERS, .changeset/config.json. If your fix requires touching any of these, do not — bail out and comment instead.
  • ./.github/barista/scripts/open-pr.ts --title "<title>" --body-file <path> — commits all changes, force-pushes the working branch, opens a draft PR linking the issue. Call exactly once, at the end.
  • ./.github/barista/scripts/add-comment.ts "body" or --file path.md — post one comment on the issue. Use this either to link the PR (success) or to explain why no PR (bailout). Exactly once.

Nothing else.

Read the full file on GitHub · 103 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.

  1. 13d ago Changed · +1 lines 713ca9929e25
  2. 1mo ago Changed 7d2b6ba3a719
  3. 1mo ago Changed b764d23cf7c2
  4. 1mo ago First seen · 102 lines · 17 tokens per session scan A 1fbe792ec291

Subscribe to this mod's changes

barista-fix is a command published in the GitHub repository frappe/frappe-ui (1,083 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 1,931 once invoked, about $0.0001 per session on Opus 5.5. 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.