feedback-ls

feedback-ls is a skill for Claude Code from AI-Riksarkivet/ra-mcp. It costs 66 tokens per session (1,650 once invoked), scanned A, original, Apache-2.0.

A workflow for sending document pages to Label Studio, a tool where people review or create annotations. It can send pages with existing text and layout annotations or blank images for annotation from scratch.

In plain words
What is it for?
It is for reviewing transcriptions, checking text-line or region boundaries, creating annotation tasks, and collecting quality feedback on document pages.
Why use it?
It moves transcription and page-layout checks into a human review process, making it easier to correct errors or create labelled examples.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the ra-mcp-tools plugin — 8 skills shipped together

Good fit It is for reviewing transcriptions, checking text-line or region boundaries, creating annotation tasks, and collecting quality feedback on document pages.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ai-riksarkivet/ra-mcp/feedback-ls
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.

Any agent
npx skills add AI-Riksarkivet/ra-mcp --skill feedback-ls
Clone the repo
git clone --depth 1 https://github.com/AI-Riksarkivet/ra-mcp

Made for: Claude Code.

Or install ra-mcp-tools, the plugin that ships this one along with the rest of its 8 skills.

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 feedback-ls

README.md
[![agentmods](https://agentmods.dev/badge/skills/ai-riksarkivet/ra-mcp/feedback-ls/github.svg)](https://agentmods.dev/skills/ai-riksarkivet/ra-mcp/feedback-ls)
Your own site
<a href="https://agentmods.dev/skills/ai-riksarkivet/ra-mcp/feedback-ls"><img src="https://agentmods.dev/badge/skills/ai-riksarkivet/ra-mcp/feedback-ls/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 feedback-ls

Your own site · 80×15
<a href="https://agentmods.dev/skills/ai-riksarkivet/ra-mcp/feedback-ls"><img src="https://agentmods.dev/badge/skills/ai-riksarkivet/ra-mcp/feedback-ls.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,650 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Privilege Escalation · line 189
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
How audits are shown
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 $0.00066 $0.01650
Opus 5 $0.00033 $0.00825
Sonnet 5 $0.00013 $0.00330
Haiku 4.5 $0.00007 $0.00165

Measured 9d ago against content hash 79bbd692fe8d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

feedback-ls 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.

plugins/ra-mcp-tools/skills/feedback-ls/SKILL.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Label Studio Feedback Workflow

Send document pages to Label Studio for human annotation and feedback.

Tool

  • label_import_to_label_studio — Import pages to a Label Studio project. Two modes:
    • With ALTO: pre-annotated tasks with polygons and transcriptions
    • Images only: blank tasks for annotation from scratch

When to Use

  • User asks to send pages for human review or annotation
  • User wants to flag transcription or segmentation issues
  • User wants to create Label Studio tasks from browse results
  • User wants to send images for annotation from scratch
  • User asks for quality assurance on specific pages

Two Modes

Mode 1: Pre-annotated (with ALTO XML)

Use when pages already have AI transcriptions. The tool fetches ALTO XML, extracts text line polygons and transcriptions, and creates VectorLabels pre-annotations.

{
  "image_urls": [
    "https://lbiiif.riksarkivet.se/arkis!30002056_00004/full/max/0/default.jpg"
  ],
  "alto_urls": [
    "https://sok.riksarkivet.se/dokument/alto/SE_RA_30002056_00004"
  ],
  "feedback": [["Transcription"]]
}

Mode 2: Images only (no ALTO)

Use when there are no existing transcriptions — the user wants to annotate from scratch. Just pass image URLs, omit alto_urls.

{
  "image_urls": [
    "https://lbiiif.riksarkivet.se/arkis!30002056_00004/full/max/0/default.jpg",
    "https://lbiiif.riksarkivet.se/arkis!30002056_00005/full/max/0/default.jpg"
  ]
}

Choosing the Right Source for Pre-annotations

When the user wants to send pages with pre-annotations, choose the source based on what's available:

Situation Source How
Pages from browse_document results ALTO XML from Riksarkivet Pass alto_urls from browse output
User has images without transcriptions No pre-annotations Omit alto_urls (image-only mode)
User has images and wants AI transcription first HTR transcription Use htr_transcribe first to generate ALTO XML, then pass the ALTO export URLs as alto_urls
User wants to label/annotate themselves No pre-annotations Omit alto_urls — blank tasks for manual annotation

Read the full file on GitHub · 193 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 · 193 lines · 66 tokens per session scan A 79bbd692fe8d

Subscribe to this mod's changes

feedback-ls is a skill published in the GitHub repository AI-Riksarkivet/ra-mcp (22 stars, last pushed 2d ago), licensed Apache-2.0. It adds 66 tokens to every session and 1,650 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

doc-coauthoring

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers.…

Wide-Moat/open-computer-use · 77 tokens

pdf-reading

Use this skill when you need to read, inspect, or extract content from PDF files — especially when file content is NOT in your context and you need to read it from disk. Covers content inventory, text extraction, page rasterization for visual inspection, embedded image/attachment/table/form-field extraction, and…

Wide-Moat/open-computer-use · 115 tokens

xlsx

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Assistant needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify…

Wide-Moat/open-computer-use · 96 tokens

pdf

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Assistant needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

Wide-Moat/open-computer-use · 50 tokens

pptx

Presentation creation, editing, and analysis. When Assistant needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks.

Wide-Moat/open-computer-use · 62 tokens

docx

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When the Assistant needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked…

Wide-Moat/open-computer-use · 78 tokens