review-ui

review-ui is a command for Claude Code from mjmorales/claude-prove. It costs 22 tokens per session (1,290 once invoked), scanned C, original, MIT.

A local browser-based interface for inspecting prove runs, grouped actions, and verdicts. It starts a server on the computer and can open the interface in a browser.

In plain words
What is it for?
Use it to start, stop, restart, or check the review server, choose a port, and inspect runs in the browser.
Why use it?
It gives you a visual way to examine recorded prove results instead of relying only on command-line output.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: reads .claude/ paths.

Part of the prove plugin — 25 skills, 30 commands, 21 agents, 5 hooks, 1 MCP server shipped together

Good fit Use it to start, stop, restart, or check the review server, choose a port, and inspect runs in the browser.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/mjmorales/claude-prove/review-ui
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/mjmorales/claude-prove

Made for: Claude Code.

Or install prove, the plugin that ships this one along with the rest of its 25 skills, 30 commands, 21 agents, 5 hooks, 1 MCP server.

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 review-ui

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/mjmorales/claude-prove/review-ui"><img src="https://agentmods.dev/badge/commands/mjmorales/claude-prove/review-ui.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,290 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00022 $0.01290
Opus 5 $0.00011 $0.00645
Sonnet 5 $0.00004 $0.00258
Haiku 4.5 $0.00002 $0.00129

Measured 9d ago against content hash fc106f8fbcbc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

review-ui scanned grade C with 2 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 9d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

> `claude-prove` CLI not found on PATH. Install via `curl -fsSL https://raw.githubusercontent.com/mjmorales/claude-prove/main/scripts/install.sh | bash`. Dev-mode users: alias or symlink `claude-prove` to your working-tr

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

> `claude-prove` CLI not found on PATH. Install via `curl -fsSL https://raw.githubusercontent.com/mjmorales/claude-prove/main/scripts/install.sh | bash`. Dev-mode users: alias or symlink `claude-prove` to your working-tr
commands/review-ui.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review UI

Drive the prove review UI through the in-process daemon. claude-prove review-ui serve starts, stops, queries, and restarts a detached loopback server; its pidfile and log live under ~/.claude-prove/review-ui/.

Default (no arguments): serve start → read the resolved port from its stdout → open the browser at that port.

Precondition

Check this first. On failure, print the message and stop — do nothing else.

claude-prove on PATH: run command -v claude-prove >/dev/null. If it is missing, print:

claude-prove CLI not found on PATH. Install via curl -fsSL https://raw.githubusercontent.com/mjmorales/claude-prove/main/scripts/install.sh | bash. Dev-mode users: alias or symlink claude-prove to your working-tree entry point.

Arguments

Parse $ARGUMENTS:

  • --stopserve stop, then exit. No start, no browser.
  • --statusserve status, print the JSON, then exit. No start, no browser.
  • --restartserve restart instead of serve start.
  • --port <N> — pin the listen port, bypassing machine-config resolution and the busy-port scan.
  • --no-open — start (or restart) but do not open a browser.

Empty $ARGUMENTS runs the default start-and-open flow.

Flow

Stop

When --stop is set:

claude-prove review-ui serve stop

Report the outcome and exit.

Status

When --status is set:

claude-prove review-ui serve status

status prints {"running":<bool>,"pid":<int|null>,"port":<int>} on stdout. Echo it, summarize whether the daemon is running, and exit.

Start or restart

Pick the verb from the arguments — serve restart when --restart is set, otherwise serve start. Append --port <N> only when the user passed it.

claude-prove review-ui serve start            # or: serve restart

start resolves the repo root from the current directory, resolves the port (the machine-global ~/.claude-prove/config.json::review_ui_port, then an upward scan past any busy port — a bump is warned on stderr), resolves the web bundle in the parent (a missing bundle warns on stderr and boots API-only), spawns the detached loopback child, and polls /api/health until it answers. On success it prints {"running":true,"pid":<int>,"port":<int>} on stdout. restart stops any recorded daemon first, then runs the same start path.

Read the full file on GitHub · 104 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. 9d ago First seen · 104 lines · 22 tokens per session scan C fc106f8fbcbc

Subscribe to this mod's changes

review-ui is a command published in the GitHub repository mjmorales/claude-prove (2 stars, last pushed 29d ago), licensed MIT. It adds 22 tokens to every session and 1,290 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.