ocr-quality-assurance

ocr-quality-assurance is an agent for Claude Code from davepoon/buildwithclaude. It costs 50 tokens per session (283 once invoked), scanned A, original, MIT.

An OCR review step that checks corrected text against the original scanned image. OCR, or optical character recognition, turns images of text into editable text.

In plain words
What is it for?
It is for final checks of scanned documents, extracted text, and OCR correction pipelines.
Why use it?
It catches missing words, wrong characters, formatting mistakes, and Markdown errors before the text is published or reused.

Agent for Claude Code

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

Part of the agents-media-content plugin — 11 agents shipped together

Good fit It is for final checks of scanned documents, extracted text, and OCR correction pipelines.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/davepoon/buildwithclaude/ocr-quality-assurance
About the project

davepoon/buildwithclaude is a discovery hub and plugin marketplace for Claude Code extensions, including agents, commands, hooks, skills, plugins, MCP servers, and marketplace collections. Developers use it to browse, search, and find installation instructions for tools that extend Claude-related workflows. Catalogue entries include agents, plugins, commands, and skills from this collection.

davepoon/buildwithclaude · 3,421 stars · on GitHub · buildwithclaude.com

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/davepoon/buildwithclaude

Made for: Claude Code.

Or install agents-media-content, the plugin that ships this one along with the rest of its 11 agents.

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 ocr-quality-assurance

README.md
[![agentmods](https://agentmods.dev/badge/agents/davepoon/buildwithclaude/ocr-quality-assurance.svg)](https://agentmods.dev/agents/davepoon/buildwithclaude/ocr-quality-assurance)
Your own site
<a href="https://agentmods.dev/agents/davepoon/buildwithclaude/ocr-quality-assurance"><img src="https://agentmods.dev/badge/agents/davepoon/buildwithclaude/ocr-quality-assurance.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 283 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 $0.00050 $0.00283
Opus 5 $0.00025 $0.00142
Sonnet 5 $0.00010 $0.00057
Haiku 4.5 $0.00005 $0.00028

Measured 4d ago against content hash 0dea601cb36f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ocr-quality-assurance 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 4d 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/agents-media-content/agents/ocr-quality-assurance.md · 29 lines

What it actually says

You are an OCR Quality Assurance specialist, the final gatekeeper in an OCR correction pipeline. Your expertise lies in meticulous validation and ensuring absolute fidelity between corrected text and original source images.

When invoked:

  • OCR correction pipeline has completed all processing stages
  • Final validation of corrected text against original image is needed
  • Quality assurance before publishing or using OCR-processed content
  • Verification that all corrections maintain content integrity

Process:

  1. Cross-reference every correction made by previous agents with the source image
  2. Verify all text visible in the image is accurately represented
  3. Validate formatting choices reflect the visual structure of the original
  4. Check that special characters, numbers, and punctuation match exactly
  5. Test markdown rendering and syntax correctness
  6. Flag any uncertainties requiring human review with specific context

Provide:

  • Structured validation report with overall approval status
  • Content integrity confirmation showing all content is preserved
  • Correction accuracy verification against source image evidence
  • Markdown syntax and rendering validation results
  • Flagged issues requiring human review with detailed descriptions
  • Specific recommendations for final approval or additional corrections
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. 4d ago First seen · 29 lines · 50 tokens per session scan A 0dea601cb36f

Subscribe to this mod's changes

ocr-quality-assurance is an agent published in the GitHub repository davepoon/buildwithclaude (3,421 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 283 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 2026-09-03.

Related

Other agents, from other repositories

reference-builder

Creates exhaustive technical references and API documentation. Generates comprehensive parameter listings, configuration guides, and searchable reference materials. Use PROACTIVELY for API docs, configuration references, or complete technical specifications.

NOMARJ/sigil · 41 tokens

dev-document

Generation of documents (PDF, DOCX, XLSX, PPTX). Use to create a document, generate a report, export to PDF/Word/Excel/PowerPoint, or produce an office file.

christopherlouet/claude-base · 45 tokens

archcore-assistant

Archcore documentation expert. Use for complex multi-document tasks: requirements engineering (ISO 29148 cascades), multi-document planning, relation graph management, and any task involving creation or modification of multiple .archcore/ documents.

archcore-ai/plugin · 50 tokens

document-parser-searcher

Use this agent when you need to parse, search, or analyze documents in various formats (PDF, DOCX, PPTX, etc.). Examples include: searching through research papers for specific concepts, extracting information from legal documents, finding relevant sections in technical manuals, analyzing large document collections…

sonomirco/agents-and-commands · 0 tokens

confluence-fetcher

An agent that retrieves and explains pages from Confluence, a company wiki and documentation service, using their URLs.

lc-semba-ryuichiro/semba-claude-plugins · 437 tokens

quarto-critic

Adversarial QA agent that compares Quarto HTML against Beamer PDF benchmark. Produces harsh, actionable criticism. Does NOT edit files — read-only analysis only.

brycewang-stanford/Auto-Empirical-Research-Skills · 38 tokens