CodexBar macOS Release
steipete/CodexBar
Releases a signed, notarized CodexBar build: confirms the changelog, resolves signing credentials from 1Password, runs the release script in tmux, and updates the Sparkle appcast and Homebrew tap.
Covers Daytona CLI setup, sandbox debugging, keeping a sandbox alive and which credentials the CLI uses, for when Daytona itself is the problem rather than the tests.
Install Daytona Sandbox Operations
$ npx skills add different-ai/openwork --skill daytona -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install different-ai/openwork daytona --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/different-ai/openwork.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.opencode/skills/daytona .claude/skills/daytona && rm -rf skills-srcUse ~/.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/
Install the "daytona" agent skill from https://github.com/different-ai/openwork/tree/dev/.opencode/skills/daytona into .claude/skills/daytona/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "daytona", 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 install https://github.com/different-ai/openwork/tree/dev/.opencode/skills/daytonaType 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.
$ npx skills add different-ai/openwork --skill daytona -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install different-ai/openwork daytona --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/different-ai/openwork.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.opencode/skills/daytona .agents/skills/daytona && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "daytona" agent skill from https://github.com/different-ai/openwork/tree/dev/.opencode/skills/daytona into .agents/skills/daytona/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "daytona", 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.
$ npx skills add different-ai/openwork --skill daytona -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install different-ai/openwork daytona --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/different-ai/openwork.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.opencode/skills/daytona .cursor/skills/daytona && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "daytona" agent skill from https://github.com/different-ai/openwork/tree/dev/.opencode/skills/daytona into .cursor/skills/daytona/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "daytona", 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 https://github.com/different-ai/openwork.git --path .opencode/skills/daytona--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add different-ai/openwork --skill daytona -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install different-ai/openwork daytona --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/different-ai/openwork.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.opencode/skills/daytona .gemini/skills/daytona && rm -rf skills-srcUse ~/.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/
Install the "daytona" agent skill from https://github.com/different-ai/openwork/tree/dev/.opencode/skills/daytona into .gemini/skills/daytona/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "daytona", 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.
$ gh skill install different-ai/openwork daytonaInstalls 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).
$ npx skills add different-ai/openwork --skill daytona -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/different-ai/openwork.git skills-src && mkdir -p .github/skills && cp -r skills-src/.opencode/skills/daytona .github/skills/daytona && rm -rf skills-srcUse ~/.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/
Install the "daytona" agent skill from https://github.com/different-ai/openwork/tree/dev/.opencode/skills/daytona into .github/skills/daytona/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "daytona", 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.
$ npx skills add different-ai/openwork --skill daytona -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install different-ai/openwork daytona --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/different-ai/openwork.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.opencode/skills/daytona .opencode/skills/daytona && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "daytona" agent skill from https://github.com/different-ai/openwork/tree/dev/.opencode/skills/daytona into .opencode/skills/daytona/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "daytona", 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
daytona- GitHub stars
- 24k
- Token cost
- ~917 tokens
- SKILL.md length
- 403 words
- Files
- 1
- Skills in repo
- 33
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Covers Daytona CLI setup, sandbox debugging, keeping a sandbox alive and which credentials the CLI uses, for when Daytona itself is the problem rather than the tests.
- Setting up and authenticating the Daytona CLI
- SKILL.md covers Setup, Long-lived manual Electron…, Long-lived manual server sandbox and Debugging, plus 3 more sections
- Calls bash, brew and pnpm; needs DAYTONA_API_KEY
- Debugging a Daytona sandbox that fails with a memory-limit error
What it does
This skill is for Daytona infrastructure problems, not for deciding where tests run. Setup means installing the CLI with Homebrew and running daytona login. Much of the content explains which identity the CLI uses: the DAYTONA_API_KEY variable counts only when DAYTONA_API_URL is also set, otherwise the CLI silently falls back to the saved profile in its config directory, which you can point at an empty folder to test the not-logged-in path.
It warns against running daytona login with an API key on someone else's machine for a one-off task, since that overwrites their profile and browser login, and describes a personal-organization trap: a personal org has a 10 GiB total memory cap and none of the team's warm snapshots, so multi-sandbox previews fail with a memory-limit error. A CLI and API version mismatch warning is usually harmless. A devcontainer helper script starts long-lived manual Electron sandboxes, and test runs are redirected to a separate pnpm evals command.
When your agent uses it
- Setting up and authenticating the Daytona CLI
- Debugging a Daytona sandbox that fails with a memory-limit error
- Keeping a Daytona sandbox alive for manual exploration
Example prompts
- “Install the Daytona CLI and log in so I can create sandboxes.”
- “My multi-sandbox preview fails with a memory-limit error on Daytona, so check which organization I am logged into.”
- “Why does the Daytona CLI ignore my DAYTONA_API_KEY?”
Requirements
- Homebrew to install the Daytona CLI
- A Daytona account
What it can do on your machine
Read from SKILL.md and the folder at commit 9ce20f8. 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
Shell commands in SKILL.md call:
bashbrewpnpm
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use pnpm, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
DAYTONA_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Daytona Sandbox Operations loads about 917 tokens when it runs. Until then it costs about 45 tokens; SKILL.md has 403 words of instructions outside code blocks.
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
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 403 words (~917 tokens).
“Use this skill for Daytona infrastructure, not test placement.”
- name
- daytona
Files
Just SKILL.md in .opencode/skills/daytona of different-ai/openwork.
Open the folder on GitHubat commit 9ce20f8
Compare with similar skills
Daytona Sandbox Operations 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Daytona Sandbox Operations this skilldifferent-ai/openwork | 24k | — | ~917 | Automated safety check: Pass | Custom licence | |
| CodexBar macOS Releasesteipete/CodexBar | 22k | — | ~1.5k | Automated safety check: Pass | MIT | |
| Debugsbusso/claudeclaw | 194 | 1 repos | ~3.3k | Automated safety check: Notes | MIT | |
| Dotenvx Secretskortix-ai/suna | 20k | — | ~4.2k | Automated safety check: Notes | Custom licence | |
| CLI Channel Debuggingmicrosoft/aspire | 6.3k | — | ~6.4k | Automated safety check: Pass | MIT | |
| China Mirror ResolverLeoYeAI/openclaw-master-skills | 2.2k | — | ~4.6k | Automated safety check: Notes | MIT |
Similar skills
Debug
sbusso/claudeclaw
Debug container agent issues. An agent skill from sbusso/claudeclaw.
Dotenvx Secrets
kortix-ai/suna
How this repo manages API secrets and the four local-run environments (local/dev/staging/prod).
- Official
CLI Channel Debugging
microsoft/aspire
Emulates any Aspire CLI build identity (channel, version, commit, package source) from a locally built CLI using ASPIRECLI environment variables and the install sidecar, so a reported bug can be…
China Mirror Resolver
LeoYeAI/openclaw-master-skills
Self-healing China mirror source resolver. An agent skill from LeoYeAI/openclaw-master-skills.
Local Dev Setup
mohitagw15856/pm-claude-skills
Write a local development environment setup guide for a service or project — covering prerequisites, repository setup, environment variables, local service dependencies, database seeding, running…
More from different-ai/openwork
All 33 skills in this repoOpenWork Desktop CDP Driver
different-ai/openwork
Drives a running OpenWork desktop window over CDP from the shell to evaluate JS, take screenshots, start sessions and send prompts for hand checks.
Fake Model Provider Faults
different-ai/openwork
Makes the desktop app's model provider fail on demand, with refused connections, resets, stalls and HTTP 4xx and 5xx errors, so error and retry states can be reproduced.
OpenWork Model Alias Manager
different-ai/openwork
Manages OpenWork's inference model aliases, discounts and overlays over the upstream OpenRouter catalog, and triggers the GitHub workflow that refreshes base models.
Reproduce Chat States
different-ai/openwork
Fires known chat states in the running OpenWork desktop app, such as provider errors, retries and tool steps, so you can check how each renders.
OpenWork Electron Browser Automation
different-ai/openwork
Attaches OpenCode browser tools to the OpenWork Electron dev app through CDP to explore its UI, send a composer task and debug, not to give test verdicts.
Daytona Seeded Cloud Demo
different-ai/openwork
Spins up a persistent OpenWork Cloud Den demo on a Daytona sandbox, seeds it with Acme Robotics data and returns shareable URLs and login details.
Related
Categories
Questions about Daytona Sandbox Operations
What does Daytona Sandbox Operations do?
Covers Daytona CLI setup, sandbox debugging, keeping a sandbox alive and which credentials the CLI uses, for when Daytona itself is the problem rather than the tests. This skill is for Daytona infrastructure problems, not for deciding where tests run. Setup means installing the CLI with Homebrew and running daytona login.
When should I use Daytona Sandbox Operations?
Daytona Sandbox Operations fits situations like: setting up and authenticating the Daytona CLI; debugging a Daytona sandbox that fails with a memory-limit error; keeping a Daytona sandbox alive for manual exploration.
How do I install Daytona Sandbox Operations in Claude Code?
Run `npx skills add different-ai/openwork --skill daytona -a claude-code`. Or copy the skill folder (.opencode/skills/daytona in different-ai/openwork) into .claude/skills/daytona in your project. Claude Code loads it when a task matches its description.
How do I install Daytona Sandbox Operations in Codex?
Run `npx skills add different-ai/openwork --skill daytona -a codex`. Or copy the skill folder (.opencode/skills/daytona in different-ai/openwork) into .agents/skills/daytona in your project. Codex loads it when a task matches its description.
Can I use Daytona Sandbox Operations 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 different-ai/openwork --skill daytona -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/daytona, .gemini/skills/daytona, .github/skills/daytona and .opencode/skills/daytona in your project.
What does Daytona Sandbox Operations need to run?
Going by SKILL.md and its folder, Daytona Sandbox Operations needs the command-line tools its instructions call (bash, brew and pnpm) and credentials named DAYTONA_API_KEY. Our summary lists: Homebrew to install the Daytona CLI; A Daytona account.
Does Daytona Sandbox Operations 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 Daytona Sandbox Operations 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 Daytona Sandbox Operations use?
Daytona Sandbox Operations has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does Daytona Sandbox Operations use?
About 917 tokens (SKILL.md is roughly 3.7k 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 Daytona Sandbox Operations?
Skills that share tags, products or a category with Daytona Sandbox Operations: CodexBar macOS Release (steipete/CodexBar, 22k stars), Debug (sbusso/claudeclaw, 194 stars), Dotenvx Secrets (kortix-ai/suna, 20k stars) and CLI Channel Debugging (microsoft/aspire, 6.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Daytona Sandbox Operations?
different-ai (a GitHub organization) maintains it in different-ai/openwork, which has 23,943 GitHub stars. The repository holds 33 skills in this directory. The repository was last updated on October 8, 2026.
Source: different-ai/openwork on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.