Agent skill

Sandbox OCR

Read the text in an image from a Code node or CodeAct action, with tesseract.js running on the host

AGPL-3.0Auto-check passedDocuments & Office

Install Sandbox OCR

skills CLI

$ npx skills add nodetool-ai/nodetool --skill sandbox-ocr -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install nodetool-ai/nodetool sandbox-ocr --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/nodetool-ai/nodetool.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/sandbox-packs/sandbox-ocr .claude/skills/sandbox-ocr && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "sandbox-ocr" agent skill from https://github.com/nodetool-ai/nodetool/tree/main/packages/sandbox-packs/sandbox-ocr into .claude/skills/sandbox-ocr/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sandbox-ocr", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/nodetool-ai/nodetool/tree/main/packages/sandbox-packs/sandbox-ocr

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add nodetool-ai/nodetool --skill sandbox-ocr -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install nodetool-ai/nodetool sandbox-ocr --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/nodetool-ai/nodetool.git skills-src && mkdir -p .agents/skills && cp -r skills-src/packages/sandbox-packs/sandbox-ocr .agents/skills/sandbox-ocr && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "sandbox-ocr" agent skill from https://github.com/nodetool-ai/nodetool/tree/main/packages/sandbox-packs/sandbox-ocr into .agents/skills/sandbox-ocr/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sandbox-ocr", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add nodetool-ai/nodetool --skill sandbox-ocr -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install nodetool-ai/nodetool sandbox-ocr --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/nodetool-ai/nodetool.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/packages/sandbox-packs/sandbox-ocr .cursor/skills/sandbox-ocr && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "sandbox-ocr" agent skill from https://github.com/nodetool-ai/nodetool/tree/main/packages/sandbox-packs/sandbox-ocr into .cursor/skills/sandbox-ocr/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sandbox-ocr", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/nodetool-ai/nodetool.git --path packages/sandbox-packs/sandbox-ocr

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add nodetool-ai/nodetool --skill sandbox-ocr -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install nodetool-ai/nodetool sandbox-ocr --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/nodetool-ai/nodetool.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/packages/sandbox-packs/sandbox-ocr .gemini/skills/sandbox-ocr && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "sandbox-ocr" agent skill from https://github.com/nodetool-ai/nodetool/tree/main/packages/sandbox-packs/sandbox-ocr into .gemini/skills/sandbox-ocr/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sandbox-ocr", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install nodetool-ai/nodetool sandbox-ocr

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add nodetool-ai/nodetool --skill sandbox-ocr -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/nodetool-ai/nodetool.git skills-src && mkdir -p .github/skills && cp -r skills-src/packages/sandbox-packs/sandbox-ocr .github/skills/sandbox-ocr && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "sandbox-ocr" agent skill from https://github.com/nodetool-ai/nodetool/tree/main/packages/sandbox-packs/sandbox-ocr into .github/skills/sandbox-ocr/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sandbox-ocr", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add nodetool-ai/nodetool --skill sandbox-ocr -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install nodetool-ai/nodetool sandbox-ocr --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/nodetool-ai/nodetool.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/packages/sandbox-packs/sandbox-ocr .opencode/skills/sandbox-ocr && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "sandbox-ocr" agent skill from https://github.com/nodetool-ai/nodetool/tree/main/packages/sandbox-packs/sandbox-ocr into .opencode/skills/sandbox-ocr/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sandbox-ocr", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: sandbox-ocr
GitHub stars: 560
Token cost: ~424 tokens
SKILL.md length: 197 words
Files: 2
Skills in repo: 127
Repo updated: Oct 10, 2026
First seen: Oct 7, 2026
Licence: AGPL-3.0

At a glance

Read the text in an image from a Code node or CodeAct action, with tesseract.js running on the host

Documents & Office work in your project
SKILL.md covers recognize — image bytes to text and Gotchas
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Sandbox OCR is an agent skill from nodetool-ai/nodetool. Read the text in an image from a Code node or CodeAct action, with tesseract.js running on the host

Its SKILL.md is about 420 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `package.json`).

It sits in Documents & Office. The repository describes itself as: Agent-first Creative Workspace. The licence is AGPL-3.0.

When your agent uses it

Documents & Office work in your project

Example prompts

“/sandbox-ocr”

What it can do on your machine

Read from SKILL.md and the folder at commit 339f069. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are javascript).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Sandbox OCR loads about 424 tokens when it runs. Until then it costs about 28 tokens; SKILL.md has 197 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~28
When it runs · the whole SKILL.md, loaded when a task matches: ~424

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from nodetool-ai/nodetool at commit 339f069, republished under its AGPL-3.0 licence (© nodetool-ai). 197 words, ~424 tokens.

Download SKILL.mdSave it as .claude/skills/sandbox-ocr/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.

name: sandbox-ocr
description: Read the text in an image from a Code node or CodeAct action, with tesseract.js running on the host

OCR in the sandbox

Specifier: @nodetool-ai/sandbox-ocr. Import it at the top of the body.

tesseract.js runs a WASM engine, spawns workers, and downloads its language data on first use — none of which the guest can do. This pack is a host module: the import resolves to a generated facade over NodeTool's own implementation.

recognize — image bytes to text

import { recognize } from "@nodetool-ai/sandbox-ocr";

const { text, confidence, words } = await recognize(
  await workspace.readBytes("receipt.png")
);
const total = words.find((w) => /^\d+[.,]\d{2}$/.test(w.text));
return { text, confidence, total: total?.text ?? null };

One call gives you all three readings:

text — the whole page as one string.
confidence — the page mean, 0–100.
words — {text, confidence, bbox: {x, y, width, height}} per word, in reading order, with the box in image pixels.

Pass { language: "eng+deu" } for anything other than English; the codes are Tesseract's, +-joined. The data file for a language it has not seen before is downloaded the first time you ask for it, so that call is slower.

Get the bytes from workspace.readBytes, from await response.bytes(), or from an asset with assetToSandbox.

Gotchas

recognize is async, and the first call to it pays for engine startup.
10 MB per image. Larger input is refused by name.
20 000 words per page.
Straight, sharp scans read best. Use image.rotate and image.adjust to deskew and raise contrast before you hand the bytes over.

Files

SKILL.md and 1 other file in packages/sandbox-packs/sandbox-ocr of nodetool-ai/nodetool.

SKILL.md
package.json

Open the folder on GitHubat commit 339f069

Compare with similar skills

Sandbox OCR next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Sandbox OCR compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Sandbox OCR this skillnodetool-ai/nodetool	560	—	~424	Automated safety check: Pass	AGPL-3.0	today
Markdown Article FormatterJimLiu/baoyu-skills	27k	6 repos	~3.5k	Automated safety check: Pass	MIT	29 days ago
MarkitdownImCa0/just-laws	781	14 repos	~3.2k	Automated safety check: Notes	MIT	3 days ago
Obsidian MarkdownAtmosphere/atmosphere	3.8k	20 repos	~1.3k	Automated safety check: Pass	Apache-2.0	yesterday
DOCXrvdbreemen/OTGW-firmware	207	33 repos	~4.3k	Automated safety check: Pass	Proprietary	3 days ago
Word Document Reader and WriterHKUDS/DeepTutor	41k	—	~2.5k	Automated safety check: Pass	Apache-2.0	2 days ago

Similar skills

Markdown Article Formatter
JimLiu/baoyu-skills
Reformats plain text or Markdown articles with frontmatter, a title, a summary, headings, bold, lists and code blocks, and saves a separate formatted copy.
27k GitHub starsUsed in 6 repos~3.5k tokens
Documents & OfficeAuto-check passed
Markitdown
ImCa0/just-laws
Convert files and office documents to Markdown. An agent skill from ImCa0/just-laws.
781 GitHub starsUsed in 14 repos~3.2k tokens
Documents & OfficeAuto-check: notes
Obsidian Markdown
Atmosphere/atmosphere
Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax.
3.8k GitHub starsUsed in 20 repos~1.3k tokens
Documents & OfficeAuto-check passed
DOCX
rvdbreemen/OTGW-firmware
A skill your agent uses whenever the user wants to create, read, edit, or manipulate Word documents (.docx files).
207 GitHub starsUsed in 33 repos~4.3k tokens
Documents & OfficeAuto-check passed
Word Document Reader and Writer
HKUDS/DeepTutor
Reads, creates and edits Word .docx files with python-docx, and drops to raw OOXML for tracked changes, comments and byte-exact edits.
41k GitHub stars~2.5k tokensUpdated 2 days ago
Documents & OfficeAuto-check passed
Crossposting
wasp-lang/wasp
Crosspost Wasp blog articles (MDX) to DEV.to and Medium. An agent skill from wasp-lang/wasp.
19k GitHub stars~1.1k tokensUpdated today
Documents & OfficeAuto-check passed

More from nodetool-ai/nodetool

All 127 skills in this repo

Beat Sync Editing
nodetool-ai/nodetool
Cut a NodeTool timeline to music and shape its pacing — detect the beat grid, place cuts on phrases, pick a cut type, build speed ramps with time remap, and give the piece an arc.
560 GitHub stars~2.6k tokensUpdated today
Auto-check passed
Caption Titles
nodetool-ai/nodetool
Add and animate a consistent text layer on an existing NodeTool timeline.
560 GitHub stars~1.9k tokensUpdated today
Auto-check passed
Color Motion
nodetool-ai/nodetool
Choose and animate colour on a NodeTool timeline, including shape and text gradients, colour grades, 3D LUTs, and dither.
560 GitHub stars~2.3k tokensUpdated today
Auto-check passed
Commercial Beat Sheet
nodetool-ai/nodetool
Write a shootable, precisely timed commercial beat sheet and store it as a NodeTool storyboard, with a consistent entity roster behind every shot.
560 GitHub stars~4.6k tokensUpdated today
Auto-check passed
Elevenlabs Audio Prompting
nodetool-ai/nodetool
Direct ElevenLabs speech, dialogue, sound effects and music — the bracketed audio tags v3 acts on and why the voice decides whether a tag lands, stability as the delivery dial, punctuation instead…
560 GitHub stars~1.9k tokensUpdated today
Auto-check passed
Frame Composition
nodetool-ai/nodetool
Stage the frame on a NodeTool timeline — grids, focal placement, safe areas per aspect ratio, depth layers and parallax, camera moves, and where elements enter and leave.
560 GitHub stars~3.5k tokensUpdated today
Auto-check passed

Questions about Sandbox OCR

What does Sandbox OCR do?

Read the text in an image from a Code node or CodeAct action, with tesseract.js running on the host. Sandbox OCR is an agent skill from nodetool-ai/nodetool.

When should I use Sandbox OCR?

Sandbox OCR fits situations like: documents & Office work in your project.

How do I install Sandbox OCR in Claude Code?

Run `npx skills add nodetool-ai/nodetool --skill sandbox-ocr -a claude-code`. Or copy the skill folder (packages/sandbox-packs/sandbox-ocr in nodetool-ai/nodetool) into .claude/skills/sandbox-ocr in your project. Claude Code loads it when a task matches its description.

How do I install Sandbox OCR in Codex?

Run `npx skills add nodetool-ai/nodetool --skill sandbox-ocr -a codex`. Or copy the skill folder (packages/sandbox-packs/sandbox-ocr in nodetool-ai/nodetool) into .agents/skills/sandbox-ocr in your project. Codex loads it when a task matches its description.

Can I use Sandbox OCR in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add nodetool-ai/nodetool --skill sandbox-ocr -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sandbox-ocr, .gemini/skills/sandbox-ocr, .github/skills/sandbox-ocr and .opencode/skills/sandbox-ocr in your project.

What does Sandbox OCR need to run?

SKILL.md names no scripts, command-line tools or credentials: Sandbox OCR is instructions for the agent only.

Does Sandbox OCR access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Sandbox OCR safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Sandbox OCR use?

Sandbox OCR is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Sandbox OCR use?

About 424 tokens (SKILL.md is roughly 1.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Sandbox OCR?

Skills that share tags, products or a category with Sandbox OCR: Markdown Article Formatter (JimLiu/baoyu-skills, 27k stars), Markitdown (ImCa0/just-laws, 781 stars), Obsidian Markdown (Atmosphere/atmosphere, 3.8k stars) and DOCX (rvdbreemen/OTGW-firmware, 207 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Sandbox OCR?

nodetool-ai (a GitHub organization) maintains it in nodetool-ai/nodetool, which has 560 GitHub stars. The repository holds 127 skills in this directory. The repository was last updated on October 10, 2026.

Source: nodetool-ai/nodetool on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Sandbox OCR

Facts

At a glance

What it does

When your agent uses it

Example prompts

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

OCR in the sandbox

recognize — image bytes to text

Gotchas

Files

Compare with similar skills

Similar skills

More from nodetool-ai/nodetool

Related

Questions about Sandbox OCR