Daytona Sandbox Operations
different-ai/openwork
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.
Delete stale Daytona sandboxes across ALL THREE orgs (DataComp, DataCompData, DataCompRL) in one pass.
Apache-2.0Auto-check passed
Install Utils Cleanup Stale Sandboxes
$ npx skills add open-thoughts/OpenThoughts-Agent --skill utils-cleanup-stale-sandboxes -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install open-thoughts/OpenThoughts-Agent utils-cleanup-stale-sandboxes --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/open-thoughts/OpenThoughts-Agent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/utils-cleanup-stale-sandboxes .claude/skills/utils-cleanup-stale-sandboxes && 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 "utils-cleanup-stale-sandboxes" agent skill from https://github.com/open-thoughts/OpenThoughts-Agent/tree/main/.agents/skills/utils-cleanup-stale-sandboxes into .claude/skills/utils-cleanup-stale-sandboxes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "utils-cleanup-stale-sandboxes", 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/open-thoughts/OpenThoughts-Agent/tree/main/.agents/skills/utils-cleanup-stale-sandboxesType 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 open-thoughts/OpenThoughts-Agent --skill utils-cleanup-stale-sandboxes -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install open-thoughts/OpenThoughts-Agent utils-cleanup-stale-sandboxes --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/open-thoughts/OpenThoughts-Agent.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/utils-cleanup-stale-sandboxes .agents/skills/utils-cleanup-stale-sandboxes && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "utils-cleanup-stale-sandboxes" agent skill from https://github.com/open-thoughts/OpenThoughts-Agent/tree/main/.agents/skills/utils-cleanup-stale-sandboxes into .agents/skills/utils-cleanup-stale-sandboxes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "utils-cleanup-stale-sandboxes", 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 open-thoughts/OpenThoughts-Agent --skill utils-cleanup-stale-sandboxes -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install open-thoughts/OpenThoughts-Agent utils-cleanup-stale-sandboxes --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/open-thoughts/OpenThoughts-Agent.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/utils-cleanup-stale-sandboxes .cursor/skills/utils-cleanup-stale-sandboxes && 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 "utils-cleanup-stale-sandboxes" agent skill from https://github.com/open-thoughts/OpenThoughts-Agent/tree/main/.agents/skills/utils-cleanup-stale-sandboxes into .cursor/skills/utils-cleanup-stale-sandboxes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "utils-cleanup-stale-sandboxes", 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/open-thoughts/OpenThoughts-Agent.git --path .agents/skills/utils-cleanup-stale-sandboxes--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 open-thoughts/OpenThoughts-Agent --skill utils-cleanup-stale-sandboxes -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install open-thoughts/OpenThoughts-Agent utils-cleanup-stale-sandboxes --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/open-thoughts/OpenThoughts-Agent.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/utils-cleanup-stale-sandboxes .gemini/skills/utils-cleanup-stale-sandboxes && 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 "utils-cleanup-stale-sandboxes" agent skill from https://github.com/open-thoughts/OpenThoughts-Agent/tree/main/.agents/skills/utils-cleanup-stale-sandboxes into .gemini/skills/utils-cleanup-stale-sandboxes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "utils-cleanup-stale-sandboxes", 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 open-thoughts/OpenThoughts-Agent utils-cleanup-stale-sandboxesInstalls 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 open-thoughts/OpenThoughts-Agent --skill utils-cleanup-stale-sandboxes -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/open-thoughts/OpenThoughts-Agent.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/utils-cleanup-stale-sandboxes .github/skills/utils-cleanup-stale-sandboxes && 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 "utils-cleanup-stale-sandboxes" agent skill from https://github.com/open-thoughts/OpenThoughts-Agent/tree/main/.agents/skills/utils-cleanup-stale-sandboxes into .github/skills/utils-cleanup-stale-sandboxes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "utils-cleanup-stale-sandboxes", 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 open-thoughts/OpenThoughts-Agent --skill utils-cleanup-stale-sandboxes -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install open-thoughts/OpenThoughts-Agent utils-cleanup-stale-sandboxes --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/open-thoughts/OpenThoughts-Agent.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/utils-cleanup-stale-sandboxes .opencode/skills/utils-cleanup-stale-sandboxes && 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 "utils-cleanup-stale-sandboxes" agent skill from https://github.com/open-thoughts/OpenThoughts-Agent/tree/main/.agents/skills/utils-cleanup-stale-sandboxes into .opencode/skills/utils-cleanup-stale-sandboxes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "utils-cleanup-stale-sandboxes", 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
utils-cleanup-stale-sandboxes- GitHub stars
- 301
- Token cost
- ~819 tokens
- SKILL.md length
- 224 words
- Files
- 1
- Skills in repo
- 44
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Delete stale Daytona sandboxes across ALL THREE orgs (DataComp, DataCompData, DataCompRL) in one pass.
- The Daytona sandbox count is climbing (eval/datagen/RL sandboxes left behind after jobs finish)
- SKILL.md covers When to use, The three orgs, How to invoke and Flags, plus 1 more section
- Calls python; needs DAYTONA_API_KEY and DAYTONA_RL_API_KEY
- A sweep flags stale sandboxes
What it does
Utils Cleanup Stale Sandboxes is an agent skill from open-thoughts/OpenThoughts-Agent. Delete stale Daytona sandboxes across ALL THREE orgs (DataComp, DataCompData, DataCompRL) in one pass. Runs scripts/daytona/cleanupstalesandboxes.py three times — once per org — each time setting the org's API key via --api-key-env so the script queries and deletes in the correct org. Default threshold is 60 minutes of inactivity; --delete actually removes them (dry run otherwise). Use when the Daytona sandbox count is climbing (eval/datagen/RL sandboxes left behind after jobs finish), when a sweep flags stale…
Its SKILL.md is about 820 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: Data recipes and robust infrastructure for training AI agents. The licence is Apache-2.0.
When your agent uses it
- The Daytona sandbox count is climbing (eval/datagen/RL sandboxes left behind after jobs finish)
- A sweep flags stale sandboxes
- Approaching the org snapshot/sandbox cap
Example prompts
- “/utils-cleanup-stale-sandboxes”
Requirements
- Python 3
- A credential in DAYTONA_API_KEY
- A credential in DAYTONA_DATA_API_KEY
What it can do on your machine
Read from SKILL.md and the folder at commit 3bd1917. 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:
python
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:
DAYTONA_API_KEYDAYTONA_RL_API_KEYDAYTONA_DATA_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Utils Cleanup Stale Sandboxes loads about 819 tokens when it runs. Until then it costs about 154 tokens; SKILL.md has 224 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
The full file from open-thoughts/OpenThoughts-Agent at commit 3bd1917, republished under its Apache-2.0 licence (© open-thoughts). 224 words, ~819 tokens.
Download SKILL.mdSave it as
.claude/skills/utils-cleanup-stale-sandboxes/SKILL.md (or your agent's skills folder).- name
- utils-cleanup-stale-sandboxes
- description
- Delete stale Daytona sandboxes across ALL THREE orgs (DataComp, DataCompData, DataCompRL) in one pass. Runs `scripts/daytona/cleanup_stale_sandboxes.py` three times — once per org — each time setting the org's API key via `--api-key-env` so the script queries and deletes in the correct org. Default threshold is 60 minutes of inactivity; `--delete` actually removes them (dry run otherwise). Use when the Daytona sandbox count is climbing (eval/datagen/RL sandboxes left behind after jobs finish), when a sweep flags stale sandboxes, or when approaching the org snapshot/sandbox cap.
utils-cleanup-stale-sandboxes
Delete stale Daytona sandboxes across the three orgs.
When to use
- Daytona sandbox count is climbing — stale sandboxes left behind after eval / datagen / RL jobs finish.
- A sweep flags stale sandboxes or the org approaches its cap.
- Before a large eval, datagen, or RL launch.
- Routine hygiene during heavy operations.
The three orgs
| Org | API key env var | Typical sandboxes |
|---|---|---|
| DataComp (main) | DAYTONA_API_KEY | Eval (terminus-2 agent sandboxes) |
| DataCompData | DAYTONA_DATA_API_KEY | Datagen (trace-generation rollouts) |
| DataCompRL | DAYTONA_RL_API_KEY | RL (SkyRL/GRPO agentic rollouts) |
Source $DC_AGENT_SECRET_ENV to set all three variables. --api-key-env selects the org for each invocation.
How to invoke
Locally (Mac) — uses the otagent conda env's Python:
set -a; source "${DC_AGENT_SECRET_ENV:?set DC_AGENT_SECRET_ENV to the secrets file first}"; set +a
PY=/Users/benjaminfeuer/miniconda3/envs/otagent/bin/python
SCRIPT=scripts/daytona/cleanup_stale_sandboxes.py
THRESHOLD=60 # minutes of inactivity
for KEY_ENV in DAYTONA_API_KEY DAYTONA_DATA_API_KEY DAYTONA_RL_API_KEY; do
echo "============================================"
echo "Org: $KEY_ENV"
echo "============================================"
$PY $SCRIPT --api-key-env "$KEY_ENV" --threshold "$THRESHOLD" --delete
echo
doneDry run: omit --delete.
for KEY_ENV in DAYTONA_API_KEY DAYTONA_DATA_API_KEY DAYTONA_RL_API_KEY; do
$PY $SCRIPT --api-key-env "$KEY_ENV" --threshold "$THRESHOLD"
doneCustom threshold — pass --threshold <minutes> (default 60):
# Only clean sandboxes inactive for >2 hours
THRESHOLD=120Flags
| Flag | Default | Purpose |
|---|---|---|
--delete | off (dry run) | Actually delete stale sandboxes |
--threshold | 60 | Minutes of inactivity before a sandbox is considered stale |
--api-key-env | DAYTONA_API_KEY | Which env var holds the org's API key |
Gotchas
- Must source
$DC_AGENT_SECRET_ENVfirst — all threeDAYTONA_*env vars must be set before running the loop, or the script will exit withERROR: ... not set in environment. - Run from the otagent env — the
daytonaSDK must be installed (it is in theotagentconda env; NOT in the base env). Use the full interpreter path/Users/benjaminfeuer/miniconda3/envs/otagent/bin/python. - RL (
DAYTONA_RL_API_KEY) may have long-lived sandboxes. Raise its threshold if active sandboxes are selected. - Dry run first when unsure.
© open-thoughts, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .agents/skills/utils-cleanup-stale-sandboxes of open-thoughts/OpenThoughts-Agent.
Open the folder on GitHubat commit 3bd1917
Compare with similar skills
Utils Cleanup Stale Sandboxes 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 |
|---|---|---|---|---|---|---|
| Utils Cleanup Stale Sandboxes this skillopen-thoughts/OpenThoughts-Agent | 301 | — | ~819 | Automated safety check: Pass | Apache-2.0 | |
| Daytona Sandbox Operationsdifferent-ai/openwork | 24k | — | ~917 | Automated safety check: Pass | Custom licence | |
| Cleanupsimstudioai/sim | 30k | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | |
| Agent Sandboxruvnet/ruflo | 74k | 3 repos | ~777 | Automated safety check: Pass | MIT | |
| Sandbox Benchvercel/next.js | 143k | — | ~4.1k | Automated safety check: Pass | MIT | |
| Git Worktree Cleanuplobehub/lobehub | 83k | — | ~2.8k | Automated safety check: Pass | Custom licence |
Similar skills
Cleanup
simstudioai/sim
Run all code quality skills — effects, memo, callbacks, state, React Query, emcn design review, url-state, comments, and test-audit — analyzing in parallel, then applying fixes sequentially
Agent Sandbox
ruvnet/ruflo
Agent skill for sandbox - invoke with $agent-sandbox. An agent skill from ruvnet/ruflo.
- Official
Sandbox Bench
vercel/next.js
Benchmark React or Next.js changes on Vercel Sandbox VMs with paired A/B statistics: react PR/commit vs base, or Next.js PR/commit vs base, measured end-to-end through the bench/render-pipeline app…
Git Worktree Cleanup
lobehub/lobehub
Audits stale Git worktrees and branches with a bundled script, classifies each one, and deletes only after you approve the exact candidates.
Stale Worktree Cleanup
trycompai/comp
A skill your agent uses when cleaning up old git worktrees, removing worktrees whose branches have merged or been abandoned, or dropping orphaned compdev Postgres databases.
More from open-thoughts/OpenThoughts-Agent
All 44 skills in this repoAnalyze Dataset Token Length
open-thoughts/OpenThoughts-Agent
Analyze the token length of an OT-Agent conversation-format (ShareGPT-style) dataset — the per-trace distribution (median/p90/max) and/or counts under a token threshold + a metadata predicate (e.g.
Analyze Id Eval Ranking
open-thoughts/OpenThoughts-Agent
Given a list of models (HF name stubs) that have valid agentic ID eval scores in Supabase, build a ranking table: raw per-benchmark accuracy on the 3 ID benchmarks (SWE-Bench-100…
Analyze Job History Iris
open-thoughts/OpenThoughts-Agent
Run the Iris harbor job-history analyzer (scripts/iris/analyzeirisharborjob.py) on a datagen/eval job and read its JSON sidecar for trustworthy throughput / preemption / productive-trial stats.
Analyze Rl Behavior
open-thoughts/OpenThoughts-Agent
Run the full RL behavioral-analysis pipeline (scripts/analysis/analyzerlbehavior.py) on a trained RL model to understand WHAT changed vs its pre-RL baseline, WHY, whether it PERSISTS, and its EVAL…
Analyze Training Run Iris
open-thoughts/OpenThoughts-Agent
Detailed health check for a Levanter/executor TRAINING run on the marin Iris cluster (e.g.
Code Create Staged Plan
open-thoughts/OpenThoughts-Agent
DESIGN a non-trivial codebase change (Harbor / MarinSkyRL / vLLM / OT-Agent / LLaMA-Factory) as a dependency-ordered STAGED PLAN before writing code — a feature port, a multi-step fix with parity…
Questions about Utils Cleanup Stale Sandboxes
What does Utils Cleanup Stale Sandboxes do?
Delete stale Daytona sandboxes across ALL THREE orgs (DataComp, DataCompData, DataCompRL) in one pass. Utils Cleanup Stale Sandboxes is an agent skill from open-thoughts/OpenThoughts-Agent. Delete stale Daytona sandboxes across ALL THREE orgs (DataComp, DataCompData, DataCompRL) in one pass.
When should I use Utils Cleanup Stale Sandboxes?
Utils Cleanup Stale Sandboxes fits situations like: the Daytona sandbox count is climbing (eval/datagen/RL sandboxes left behind after jobs finish); A sweep flags stale sandboxes; approaching the org snapshot/sandbox cap.
How do I install Utils Cleanup Stale Sandboxes in Claude Code?
Run `npx skills add open-thoughts/OpenThoughts-Agent --skill utils-cleanup-stale-sandboxes -a claude-code`. Or copy the skill folder (.agents/skills/utils-cleanup-stale-sandboxes in open-thoughts/OpenThoughts-Agent) into .claude/skills/utils-cleanup-stale-sandboxes in your project. Claude Code loads it when a task matches its description.
How do I install Utils Cleanup Stale Sandboxes in Codex?
Run `npx skills add open-thoughts/OpenThoughts-Agent --skill utils-cleanup-stale-sandboxes -a codex`. Or copy the skill folder (.agents/skills/utils-cleanup-stale-sandboxes in open-thoughts/OpenThoughts-Agent) into .agents/skills/utils-cleanup-stale-sandboxes in your project. Codex loads it when a task matches its description.
Can I use Utils Cleanup Stale Sandboxes 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 open-thoughts/OpenThoughts-Agent --skill utils-cleanup-stale-sandboxes -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/utils-cleanup-stale-sandboxes, .gemini/skills/utils-cleanup-stale-sandboxes, .github/skills/utils-cleanup-stale-sandboxes and .opencode/skills/utils-cleanup-stale-sandboxes in your project.
What does Utils Cleanup Stale Sandboxes need to run?
Going by SKILL.md and its folder, Utils Cleanup Stale Sandboxes needs the command-line tools its instructions call (python) and credentials named DAYTONA_API_KEY, DAYTONA_RL_API_KEY and DAYTONA_DATA_API_KEY. Our summary lists: Python 3; A credential in DAYTONA_API_KEY; A credential in DAYTONA_DATA_API_KEY.
Does Utils Cleanup Stale Sandboxes 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 Utils Cleanup Stale Sandboxes 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 Utils Cleanup Stale Sandboxes use?
Utils Cleanup Stale Sandboxes is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Utils Cleanup Stale Sandboxes use?
About 819 tokens (SKILL.md is roughly 3.3k 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 Utils Cleanup Stale Sandboxes?
Skills that share tags, products or a category with Utils Cleanup Stale Sandboxes: Daytona Sandbox Operations (different-ai/openwork, 24k stars), Cleanup (simstudioai/sim, 30k stars), Agent Sandbox (ruvnet/ruflo, 74k stars) and Sandbox Bench (vercel/next.js, 143k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Utils Cleanup Stale Sandboxes?
open-thoughts (a GitHub organization) maintains it in open-thoughts/OpenThoughts-Agent, which has 301 GitHub stars. The repository holds 44 skills in this directory. The repository was last updated on September 28, 2026.
Source: open-thoughts/OpenThoughts-Agent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.