markupr: Command for Claude Code

.claude/commands/review-feedback.md

review-feedback is a command for Claude Code from eddiesanjuan/markupr. It costs 0 tokens per session (579 once invoked), scanned A, original, MIT.

A command for reviewing a MarkUpR session, a structured record of someone testing or reviewing an application with spoken feedback and screenshots. It tells the agent how to inspect the report, session metadata, referenced images, and optional recording.

In plain words
What is it for?
Use it to analyze recorded application feedback, inspect the screenshots tied to each issue, and organize fixes starting with the most serious problems.
Why use it?
It turns raw review material into a prioritized action plan by extracting each feedback item’s severity, category, observation, evidence, and suggested next step.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is eddiesanjuan/markupr's own configuration. It tells Claude Code how to work on markupr itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything markupr configures →

Reuse

Borrowing it

Nothing to install: this file belongs to eddiesanjuan/markupr. 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/eddiesanjuan/markupr/main/.claude/commands/review-feedback.md
Clone the repo
git clone --depth 1 https://github.com/eddiesanjuan/markupr

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 review-feedback

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/eddiesanjuan/markupr/review-feedback"><img src="https://agentmods.dev/badge/commands/eddiesanjuan/markupr/review-feedback.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 579 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 $0.00000 $0.00579
Opus 5 $0.00000 $0.00290
Sonnet 5 $0.00000 $0.00116
Haiku 4.5 $0.00000 $0.00058

Measured 9d ago against content hash f139c9598dbf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

review-feedback 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 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.

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/review-feedback.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review markupr Session

You are reviewing a markupr session -- a structured feedback report with voice transcription and screenshots captured while a developer reviewed their application.

Instructions

  1. Read the session directory at: $ARGUMENTS

    • Read feedback-report.md for the full structured feedback with FB-XXX items
    • Read metadata.json for session context (source app, duration, environment)
    • Read each screenshot in screenshots/ that is referenced by feedback items -- these are PNG files showing exactly what the user was looking at when they spoke
    • If session-recording.webm exists, note its path (video can't be played in CLI but the screenshots provide the visual context)
  2. Parse each feedback item (FB-001, FB-002, etc.) and extract:

    • The severity (Critical / High / Medium / Low) and category (Bug / UX Issue / Suggestion / Performance / Question / General)
    • The transcribed observation (the blockquote under "What Happened")
    • Associated screenshot(s) -- READ the image files to see what the user was looking at
    • The suggested next step from the report
  3. Create an action plan prioritized by severity:

    • Critical/High items first -- bugs and broken functionality
    • Medium items next -- UX issues and performance problems
    • Low items last -- suggestions and enhancements
  4. For each item, determine the action type:

    • Code fix -- identify the file and make the change
    • UI change -- adjust layout, styling, or component behavior
    • Documentation -- update docs or add comments
    • Investigation needed -- reproduce first, then fix
    • Future enhancement -- note for backlog, no immediate action
  5. Work through items systematically:

    • State which FB-XXX item you're addressing
    • Reference the screenshot to ground your understanding in what the user saw
    • Make the code change or explain why it should be deferred
    • After each fix, note: "FB-XXX addressed"
  6. After all items are processed, provide a summary:

    • Items addressed with code changes
    • Items deferred with reasoning
    • Patterns or architectural concerns noticed across multiple feedback items

Read the full file on GitHub · 48 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 · 48 lines · 0 tokens per session scan A f139c9598dbf

Subscribe to this mod's changes

review-feedback is a command published in the GitHub repository eddiesanjuan/markupr (18 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 579 tokens. 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.