Agent skill

Openreality

by reality-opened in reality-opened/openreality

Drive Open Reality OS through the openreality MCP tools — scan upload, reconstruction, scene sync/query, scene agents, measurements, navigation, and robot-training exports.

BSD-2-ClauseAuto-check passedAgent Workflows

Install Openreality

skills CLI

$ npx skills add reality-opened/openreality --skill openreality -a claude-code

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

GitHub CLI

$ gh skill install reality-opened/openreality openreality --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/reality-opened/openreality.git skills-src && mkdir -p .claude/skills && cp -r skills-src/mcp/skills/openreality .claude/skills/openreality && 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 "openreality" agent skill from https://github.com/reality-opened/openreality/tree/main/mcp/skills/openreality into .claude/skills/openreality/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openreality", 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/reality-opened/openreality/tree/main/mcp/skills/openreality

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 reality-opened/openreality --skill openreality -a codex

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

GitHub CLI

$ gh skill install reality-opened/openreality openreality --agent codex

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

Manual copy

$ git clone --depth 1 https://github.com/reality-opened/openreality.git skills-src && mkdir -p .agents/skills && cp -r skills-src/mcp/skills/openreality .agents/skills/openreality && 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 "openreality" agent skill from https://github.com/reality-opened/openreality/tree/main/mcp/skills/openreality into .agents/skills/openreality/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openreality", 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 reality-opened/openreality --skill openreality -a cursor

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

GitHub CLI

$ gh skill install reality-opened/openreality openreality --agent cursor

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

Manual copy

$ git clone --depth 1 https://github.com/reality-opened/openreality.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/mcp/skills/openreality .cursor/skills/openreality && 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 "openreality" agent skill from https://github.com/reality-opened/openreality/tree/main/mcp/skills/openreality into .cursor/skills/openreality/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openreality", 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/reality-opened/openreality.git --path mcp/skills/openreality

--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 reality-opened/openreality --skill openreality -a gemini-cli

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

GitHub CLI

$ gh skill install reality-opened/openreality openreality --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/reality-opened/openreality.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/mcp/skills/openreality .gemini/skills/openreality && 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 "openreality" agent skill from https://github.com/reality-opened/openreality/tree/main/mcp/skills/openreality into .gemini/skills/openreality/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openreality", 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 reality-opened/openreality openreality

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 reality-opened/openreality --skill openreality -a github-copilot

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

Manual copy

$ git clone --depth 1 https://github.com/reality-opened/openreality.git skills-src && mkdir -p .github/skills && cp -r skills-src/mcp/skills/openreality .github/skills/openreality && 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 "openreality" agent skill from https://github.com/reality-opened/openreality/tree/main/mcp/skills/openreality into .github/skills/openreality/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openreality", 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 reality-opened/openreality --skill openreality -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 reality-opened/openreality openreality --agent opencode

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

Manual copy

$ git clone --depth 1 https://github.com/reality-opened/openreality.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/mcp/skills/openreality .opencode/skills/openreality && 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 "openreality" agent skill from https://github.com/reality-opened/openreality/tree/main/mcp/skills/openreality into .opencode/skills/openreality/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openreality", 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: openreality
GitHub stars: 280
Token cost: ~941 tokens
SKILL.md length: 421 words
Files: 1
Skills in repo: 1
Repo updated: Sep 3, 2026
First seen: Oct 7, 2026
Licence: BSD-2-Clause

At a glance

Drive Open Reality OS through the openreality MCP tools — scan upload, reconstruction, scene sync/query, scene agents, measurements, navigation, and robot-training exports.

Works in 5 steps: Sync first: workspace_list_scenes — the… → Context second: scene_card — small,… → Then act → …
The user mentions their Open Reality account
SKILL.md covers Workflow, Honesty doctrine… and Troubleshooting
Needs OPENREALITY_TOKEN

What it does

Openreality is an agent skill from reality-opened/openreality. Drive Open Reality OS through the openreality MCP tools — scan upload, reconstruction, scene sync/query, scene agents, measurements, navigation, and robot-training exports. Use whenever the user mentions their Open Reality account, scans/scenes, splats, reconstructions, scene measurements, or LeRobot/GR00T/Isaac exports of captured spaces.

Its SKILL.md is about 940 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering MCP servers. It works with Model Context Protocol. The repository describes itself as: Open Reality: phone video to AI-queryable 3D scenes. MCP tools for Claude/Codex/Cursor (npm openreality-mcp), the self-hostable broker, and the VGGT-SLAM library, in one repo… The licence is BSD-2-Clause.

When your agent uses it

The user mentions their Open Reality account
Reconstructions
Scene measurements
LeRobot/GR00T/Isaac exports of captured spaces

Example prompts

“/openreality”

Requirements

A credential in OPENREALITY_TOKEN

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

Sync first: workspace_list_scenes — the account is the sync layer; scans made on
Context second: scene_card — small, honest summary (source, metric
Then act
Uploads: workspace_upload_video (≤1 GB) / workspace_upload_recording (robot
Artifacts go to disk, never into context: artifact_fetch / artifact_fetch_splat

What it can do on your machine

Read from SKILL.md and the folder at commit 4d93d5f. 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.
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 these keys or tokens, usually read from environment variables:
- OPENREALITY_TOKEN
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Openreality loads about 941 tokens when it runs. Until then it costs about 88 tokens; SKILL.md has 421 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~88
When it runs · the whole SKILL.md, loaded when a task matches: ~941

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 reality-opened/openreality at commit 4d93d5f, republished under its BSD-2-Clause licence (© reality-opened). 421 words, ~941 tokens.

Download SKILL.mdSave it as .claude/skills/openreality/SKILL.md (or your agent's skills folder).

name: openreality
description: Drive Open Reality OS through the openreality MCP tools — scan upload, reconstruction, scene sync/query, scene agents, measurements, navigation, and robot-training exports. Use whenever the user mentions their Open Reality account, scans/scenes, splats, reconstructions, scene measurements, or LeRobot/GR00T/Isaac exports of captured spaces.

Open Reality OS

You have MCP tools (server name openreality) for a user's Open Reality account — persisted 3D scenes reconstructed from phone captures, imported splats, and robot recordings.

Workflow

Sync first: workspace_list_scenes — the account is the sync layer; scans made on the user's phone or the web appear here. new_since_last_sync tells you what's new.
Context second: scene_card <scan_id> — small, honest summary (source, metric state, objects, artifacts). @-mention openreality://scene/<scan_id> works too.
Then act:
- Deterministic questions (distances, angles, room structure, paths, exports) → scene_* / export_* tools. These are pure server routes — no LLM cost.
- Narrated / visual questions ("describe this room", "key features") → agent_chat / agent_annotate. These run the SERVER-side scene agent, which spends a bounded LLM budget from the account. Prefer agent_replay (always $0) when a recorded run already answers the question (agent_runs lists them).
Uploads: workspace_upload_video (≤1 GB) / workspace_upload_recording (robot .db) / workspace_upload_splat (.ply/.spz) → then workspace_job_wait on the job_id.
Artifacts go to disk, never into context: artifact_fetch / artifact_fetch_splat return local file paths. Exports: export_manifest (dry-run) → export_prepare → artifact_fetch of the returned key. Formats: openreality, groot_lerobot_v2, isaac_usd.

Honesty doctrine (non-negotiable — mirrors the product's own guardrails)

Units: a length is metres ONLY when the response says units: "m" (a metric anchor was applied — scale_source names it). units: "relative" means relative SLAM units: never call them metres, never convert. To unlock metres: scene_anchor with two picked points and their real distance.
Closed world: the objects from scene_list_objects are the only objects that exist. Don't invent, merge, or rename them beyond their labels.
Provenance rides along: keyframes are photos; synthetic views are RENDERS of the splat (say so); generated assets (SAM-3D completions, variants, floor patches) are generated — their meta.json says generated: true. Nav plans carry "not certified navigation" — repeat it when presenting a path.
Degraded is a state, not a failure: robot-recording scenes persist degraded (no detections, preview cloud) with a QC report under derived/demo/recordings/ — report the QC verdict rather than hiding it.
The Isaac export is metric-gated: without an anchor it is refused. That refusal is correct behavior — offer the anchor flow, don't fight the gate.
Surface server refusals as-is: 409 agent_run_active (one run per scene — attach or wait), 422 unreachable_goal (includes the nearest reachable point), 409 export_job_active.

Show full SKILL.md (56 more words)Show less

Troubleshooting

No Open Reality credentials → run openreality-mcp login --token <token> (token from the deployment's /os page URL hash after dashboard sign-in) or set OPENREALITY_TOKEN.
Tokens roll automatically at half-life; a stale (>12 h idle) credential needs a fresh login.
To develop without the real backend: openreality-mcp simulator, then point the server at it with OPENREALITY_URL=http://127.0.0.1:8973 OPENREALITY_TOKEN=sim-token.

Files

Just SKILL.md in mcp/skills/openreality of reality-opened/openreality.

Open the folder on GitHubat commit 4d93d5f

Compare with similar skills

Openreality 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.

Openreality compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Openreality this skillreality-opened/openreality	280	—	~941	Automated safety check: Pass	BSD-2-Clause	1 mo ago
MCP Server Builderanthropics/skills	180k	63 repos	~2.3k	Automated safety check: Pass	Apache-2.0	2 days ago
MCP Server BuildershareAI-lab/learn-claude-code	78k	4 repos	~1.2k	Automated safety check: Pass	MIT	13 days ago
MCP Integration for Pluginsanthropics/claude-plugins-official	38k	11 repos	~3.1k	Automated safety check: Pass	Apache-2.0	today
Crush Configurationcharmbracelet/crush	29k	—	~3.7k	Automated safety check: Pass	Custom licence	today
Context Mode Output Sandboxmksglu/context-mode	26k	—	~4.1k	Automated safety check: Pass	Custom licence	today

Similar skills

MCP Server Builder
anthropics/skills
Official
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
180k GitHub starsUsed in 63 repos~2.3k tokens
Agent WorkflowsAuto-check passed
MCP Server Builder
shareAI-lab/learn-claude-code
Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.
78k GitHub starsUsed in 4 repos~1.2k tokens
Agent WorkflowsAuto-check passed
MCP Integration for Plugins
anthropics/claude-plugins-official
Official
Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.
38k GitHub starsUsed in 11 repos~3.1k tokens
Agent WorkflowsAuto-check passed
Crush Configuration
charmbracelet/crush
Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.
29k GitHub stars~3.7k tokensUpdated today
Agent WorkflowsAuto-check passed
Context Mode Output Sandbox
mksglu/context-mode
Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.
26k GitHub stars~4.1k tokensUpdated today
Agent WorkflowsAuto-check passed
Warp GUI to Agent CLI Migration
warpdotdev/warp
Migrates the compatible subset of settings and global file-based MCP servers from the Warp desktop app into Warp Agent CLI without exposing credentials or state.
65k GitHub starsUsed in 1 repo~2.1k tokens
Agent WorkflowsAuto-check passed

Works with

Model Context Protocol

Questions about Openreality

What does Openreality do?

Drive Open Reality OS through the openreality MCP tools — scan upload, reconstruction, scene sync/query, scene agents, measurements, navigation, and robot-training exports. Openreality is an agent skill from reality-opened/openreality. Drive Open Reality OS through the openreality MCP tools — scan upload, reconstruction, scene sync/query, scene agents, measurements, navigation, and robot-training exports.

When should I use Openreality?

Openreality fits situations like: the user mentions their Open Reality account; reconstructions; scene measurements; leRobot/GR00T/Isaac exports of captured spaces.

How do I install Openreality in Claude Code?

Run `npx skills add reality-opened/openreality --skill openreality -a claude-code`. Or copy the skill folder (mcp/skills/openreality in reality-opened/openreality) into .claude/skills/openreality in your project. Claude Code loads it when a task matches its description.

How do I install Openreality in Codex?

Run `npx skills add reality-opened/openreality --skill openreality -a codex`. Or copy the skill folder (mcp/skills/openreality in reality-opened/openreality) into .agents/skills/openreality in your project. Codex loads it when a task matches its description.

Can I use Openreality 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 reality-opened/openreality --skill openreality -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/openreality, .gemini/skills/openreality, .github/skills/openreality and .opencode/skills/openreality in your project.

What does Openreality need to run?

Going by SKILL.md and its folder, Openreality needs credentials named OPENREALITY_TOKEN. Our summary lists: A credential in OPENREALITY_TOKEN.

Does Openreality 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 Openreality 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 Openreality use?

Openreality is published under the BSD-2-Clause licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Openreality use?

About 941 tokens (SKILL.md is roughly 3.8k 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 Openreality?

Skills that share tags, products or a category with Openreality: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 38k stars) and Crush Configuration (charmbracelet/crush, 29k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Openreality?

reality-opened (a GitHub organization) maintains it in reality-opened/openreality, which has 280 GitHub stars. The repository was last updated on September 3, 2026.

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

Install Openreality

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Open Reality OS

Workflow

Honesty doctrine (non-negotiable — mirrors the product's own guardrails)

Troubleshooting

Files

Compare with similar skills

Similar skills

MCP Server Builder

MCP Server Builder

MCP Integration for Plugins

Crush Configuration

Context Mode Output Sandbox

Warp GUI to Agent CLI Migration

Related

Questions about Openreality