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.
curl -O https://raw.githubusercontent.com/eddiesanjuan/markupr/main/.claude/commands/review-feedback.mdgit clone --depth 1 https://github.com/eddiesanjuan/markuprWrote 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.
[](https://agentmods.dev/commands/eddiesanjuan/markupr/review-feedback)<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.
<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>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 | $0.00000 | $0.00579 |
| Opus 5 | $0.00000 | $0.00290 |
| Sonnet 5 | $0.00000 | $0.00116 |
| Haiku 4.5 | $0.00000 | $0.00058 |
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.
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
-
Read the session directory at: $ARGUMENTS
- Read
feedback-report.mdfor the full structured feedback with FB-XXX items - Read
metadata.jsonfor 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.webmexists, note its path (video can't be played in CLI but the screenshots provide the visual context)
- Read
-
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
-
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
-
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
-
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"
-
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
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.
- 9d ago First seen · 48 lines · 0 tokens per session scan A f139c9598dbf
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.
Other commands, from other repositories
voxpip
Watch any video and get a transcript — even without an API key. Extends /watch with a local speech-to-text fallback.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.