subagent

ocr-grammar-fixer — Claude Code subagent: cleans up OCR text

Q: How do I install ocr-grammar-fixer in Claude?

Run `npx claude-code-templates@latest --agent ocr-extraction-team/ocr-grammar-fixer`; the agent file lands at `.claude/agents/ocr-grammar-fixer.md`.

Q: Which tools does the subagent use?

It has `Read`, `Write` and `Edit`, which covers reading a file, making the corrections and writing the result back.

A Claude subagent that fixes OCR output: character recognition errors, broken spacing, punctuation and grammar, with the original meaning kept intact.

Install into Claude Code · claude-code-templates All methods and platforms ↓

npx claude-code-templates@latest --agent ocr-extraction-team/ocr-grammar-fixer

Open on GitHub

What ocr-grammar-fixer does

The ocr-grammar-fixer subagent takes text that has already been through OCR and hunts for the usual artifacts. It knows the classic mix-ups: rn read as m, l against I and 1, 0 against O, cl against d, li against h. It also checks word boundaries, so missing or extra spaces, merged and split words, displaced punctuation and random capitalisation all get caught.

Correction runs in five passes. First it scans for odd letter combinations and spacing patterns, then reads the surrounding words to work out what was meant. After that it restores business and marketing terminology, fixes punctuation and capitalisation, and finally checks that the result reads naturally. Meaning wins over a literal character-by-character match.

It has Read, Write and Edit available, which is enough to open a file, apply fixes and save the result. By default it returns only the corrected text with no commentary; ask for the reasoning and it will show the artifacts it found. Handy when scanned documents or PDFs leave you with garbled characters and retyping by hand is not worth the time.

What it helps with

clean up recognition errors in OCR-processed text
restore missing and extra spaces between words
fix random capitalisation and displaced punctuation
recover correct spelling of business and marketing terms
turn scanned text into something publishable

Example prompts for the agent

fix the OCR errors in report.txt and save the result
clean up scan.md: spacing, capitalisation, punctuation
list the OCR artifacts you found and explain each fix

How to install ocr-grammar-fixer

1claude-code-templates

npx claude-code-templates@latest --agent ocr-extraction-team/ocr-grammar-fixer

2Manually: put the files in place

.claude/agents/ocr-grammar-fixer.md

For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

Manually: put the files in place

.codex/agents/ocr-grammar-fixer.toml

Codex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/

Manually: put the files in place

.cursor/agents/ocr-grammar-fixer.md

Cursor also reads .claude/agents/

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

Questions about ocr-grammar-fixer

How do I install ocr-grammar-fixer in Claude?

Run npx claude-code-templates@latest --agent ocr-extraction-team/ocr-grammar-fixer; the agent file lands at .claude/agents/ocr-grammar-fixer.md.

What does ocr-grammar-fixer do?

It corrects text that came out of OCR: confused characters, broken word boundaries, punctuation and capitalisation. The intended meaning of the original stays the same.

Which tools does the subagent use?

It has Read, Write and Edit, which covers reading a file, making the corrections and writing the result back.

Similar subagents

All subagents for Agent setup: memory, context, orchestration →

grammar-check phuryn Checks drafts for grammar, reasoning and flow issues, then suggests focused edits. Use it when reviewing copy, documentation or a message before sending. CX Codex +1 3,000installs PDF OCR Extraction claude-office-skills Pulls text out of scanned and image-based PDFs with OCR. Useful when a document won't let you select anything but still needs to be searchable. CX Codex +1 5,700installs silicon-paddle-ocr aotenjou Recognizes text in images through the PaddleOCR model and the SiliconFlow API. Handy when you need text out of a screenshot or photo without leaving the agent chat. CX Codex +1 1,200installs ocr-super-surya yamapan (https://github.com/aktsmm) A skill that runs OCR over images, screenshots and PDFs with Surya on GPU. Useful when a document only carries its text inside pictures. CX Codex +1 558installs transcript-fixer daymade Corrects ASR/STT errors in transcripts: homophones, garbled terms, wrong names, mixed Chinese and English. Useful for meeting notes, lectures and interviews. CX Codex +1 1,200installs xcode-build-fixer AvdLee Applies approved Xcode build optimizations and re-benchmarks them to confirm the gain. Useful once an optimization plan is signed off. CX Codex +1 3,600installs

From the same set205

The whole set →

nextjs-bundle-analyzer A Claude slash command that breaks down your Next.js bundle size and points at what to trim. 560installs frontend-dev-guidelines A skill that gives the agent one set of rules for React and TypeScript work: Suspense, lazy loading, features layout, MUI v7 and TanStack. 556installs text-comparison-validator A subagent that checks extracted text against an existing markdown file, line by line. It flags missing words, typos, formatting drift and paragraph structure problems, then reports them with line numbers. 545installs claude-d3js-skill Tells the agent how to build non-standard d3.js visualisations: network graphs, geographic maps, choreographed transitions. Useful when off-the-shelf charting libraries fall short. 531installs implement-caching-strategy A Claude slash command that reads your architecture and lays out caching layers: browser, application, database, API. 520installs setup-linting Sets up linters and quality checks in your project: ESLint, Flake8, Pylint, MyPy, Clippy. Useful when style rules need to be enforced automatically. 510installs twitter-ai-influencer-manager A subagent that posts, searches and analyses AI tweets. It keeps a list of key researcher handles and helps you engage with them. 510installs vercel-deploy-optimize Optimizes a Next.js build and ships it to Vercel, checking configs along the way and wiring up performance monitoring. 506installs