RStudio Selenium to Playwright Migration
rstudio/rstudio
Converts RStudio Python Selenium electron tests into TypeScript Playwright tests, checking each against a live RStudio before counting it as migrated.
Build a runnable reproduce→fix→verify loop for a bug or feature in a fresh sandbox, and record it as a feedback-loop doc.
Install Sandbox Feedback Loop
$ npx skills add bagofwords1/bagofwords --skill sandbox-feedback-loop -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install bagofwords1/bagofwords sandbox-feedback-loop --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/bagofwords1/bagofwords.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/sandbox-feedback-loop .claude/skills/sandbox-feedback-loop && 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 "sandbox-feedback-loop" agent skill from https://github.com/bagofwords1/bagofwords/tree/main/.agents/skills/sandbox-feedback-loop into .claude/skills/sandbox-feedback-loop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sandbox-feedback-loop", 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/bagofwords1/bagofwords/tree/main/.agents/skills/sandbox-feedback-loopType 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 bagofwords1/bagofwords --skill sandbox-feedback-loop -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install bagofwords1/bagofwords sandbox-feedback-loop --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bagofwords1/bagofwords.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/sandbox-feedback-loop .agents/skills/sandbox-feedback-loop && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "sandbox-feedback-loop" agent skill from https://github.com/bagofwords1/bagofwords/tree/main/.agents/skills/sandbox-feedback-loop into .agents/skills/sandbox-feedback-loop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sandbox-feedback-loop", 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 bagofwords1/bagofwords --skill sandbox-feedback-loop -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install bagofwords1/bagofwords sandbox-feedback-loop --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bagofwords1/bagofwords.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/sandbox-feedback-loop .cursor/skills/sandbox-feedback-loop && 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 "sandbox-feedback-loop" agent skill from https://github.com/bagofwords1/bagofwords/tree/main/.agents/skills/sandbox-feedback-loop into .cursor/skills/sandbox-feedback-loop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sandbox-feedback-loop", 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/bagofwords1/bagofwords.git --path .agents/skills/sandbox-feedback-loop--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 bagofwords1/bagofwords --skill sandbox-feedback-loop -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install bagofwords1/bagofwords sandbox-feedback-loop --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bagofwords1/bagofwords.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/sandbox-feedback-loop .gemini/skills/sandbox-feedback-loop && 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 "sandbox-feedback-loop" agent skill from https://github.com/bagofwords1/bagofwords/tree/main/.agents/skills/sandbox-feedback-loop into .gemini/skills/sandbox-feedback-loop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sandbox-feedback-loop", 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 bagofwords1/bagofwords sandbox-feedback-loopInstalls 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 bagofwords1/bagofwords --skill sandbox-feedback-loop -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/bagofwords1/bagofwords.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/sandbox-feedback-loop .github/skills/sandbox-feedback-loop && 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 "sandbox-feedback-loop" agent skill from https://github.com/bagofwords1/bagofwords/tree/main/.agents/skills/sandbox-feedback-loop into .github/skills/sandbox-feedback-loop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sandbox-feedback-loop", 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 bagofwords1/bagofwords --skill sandbox-feedback-loop -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install bagofwords1/bagofwords sandbox-feedback-loop --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bagofwords1/bagofwords.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/sandbox-feedback-loop .opencode/skills/sandbox-feedback-loop && 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 "sandbox-feedback-loop" agent skill from https://github.com/bagofwords1/bagofwords/tree/main/.agents/skills/sandbox-feedback-loop into .opencode/skills/sandbox-feedback-loop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sandbox-feedback-loop", 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-feedback-loop- GitHub stars
- 458
- Token cost
- ~857 tokens
- SKILL.md length
- 272 words
- Files
- 1
- Skills in repo
- 13
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Build a runnable reproduce→fix→verify loop for a bug or feature in a fresh sandbox, and record it as a feedback-loop doc.
- Works in 4 steps: Reproduce first. Never fix a bug you… → Isolate the root cause and cite it as… → Fix, re-run the same loop, and show the… → …
- Investigating a reported bug
- SKILL.md covers Process, Environment setup (fresh…, Doc template and Rules
- Calls uv, pip and playwright
What it does
Sandbox Feedback Loop is an agent skill from bagofwords1/bagofwords. Build a runnable reproduce→fix→verify loop for a bug or feature in a fresh sandbox, and record it as a feedback-loop doc. Use when investigating a reported bug, validating a root cause, or proving a fix works — before and after the change.
Its SKILL.md is about 860 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 Testing & QA, covering Root cause analysis. It works with Python and Playwright. The repository describes itself as: Chat with your data - with memory, rules, and observability built in. Deploy in 2 minutes.
When your agent uses it
- Investigating a reported bug
- Validating a root cause
- Proving a fix works — before and after the change
Example prompts
- “/sandbox-feedback-loop”
Requirements
- Python 3
- Docker
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Reproduce first. Never fix a bug you haven't watched fail. Write the
- Isolate the root cause and cite it as file.py:line references.
- Fix, re-run the same loop, and show the observed output flipping.
- Write the doc to docs/feedback-loops/.md (do NOT add new
What it can do on your machine
Read from SKILL.md and the folder at commit ed624e0. 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:
uvpipplaywright
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use uv and pip, 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 no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Sandbox Feedback Loop loads about 857 tokens when it runs. Until then it costs about 65 tokens; SKILL.md has 272 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 272 words (~857 tokens).
“A feedback loop is a runnable document: anyone (human or agent) can re-execute it in a fresh sandbox and observe the same failure, then the same pass after the fix. Examples of the format live in docs/feedback-loops/ (e.g. save-button.md, fabric-obo-second-admin-tables.md).”
- name
- sandbox-feedback-loop
Files
Just SKILL.md in .agents/skills/sandbox-feedback-loop of bagofwords1/bagofwords.
Open the folder on GitHubat commit ed624e0
Compare with similar skills
Sandbox Feedback Loop 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 |
|---|---|---|---|---|---|---|
| Sandbox Feedback Loop this skillbagofwords1/bagofwords | 458 | — | ~857 | Automated safety check: Pass | Custom licence | |
| RStudio Selenium to Playwright Migrationrstudio/rstudio | 5.1k | — | ~3.6k | Automated safety check: Pass | Custom licence | |
| Cloud Agents Starterscalar/scalar | 16k | — | ~1.4k | Automated safety check: Pass | MIT | |
| Codex E2E Trace Validationliaohch3/claude-tap | 3.3k | — | ~3k | Automated safety check: Pass | MIT | |
| Reprovaadin/web-components | 582 | — | ~1.3k | Automated safety check: Pass | None | |
| JS-in-HTML Testingliaohch3/claude-tap | 3.3k | — | ~924 | Automated safety check: Pass | MIT |
Similar skills
Cloud Agents Starter
scalar/scalar
Minimal starter runbook for cloud agents to install dependencies, run packages, execute tests, and troubleshoot the Scalar monorepo quickly.
Codex E2E Trace Validation
liaohch3/claude-tap
Runs a real Codex CLI session through claude-tap and produces trace evidence and viewer screenshots for pull requests that touch capture, proxying or the viewer.
Repro
vaadin/web-components
Reproduce a Vaadin web component bug from a GitHub issue in vaadin/web-components.
JS-in-HTML Testing
liaohch3/claude-tap
Tests JavaScript embedded in an HTML file in two layers: pytest checks of the logic ported to Python, and Playwright runs in a real browser for the DOM.
Diagnose
ipea/geobr
Root-cause a failing or wrong geobr call with a disciplined check-the-environment-first loop instead of guessing.
More from bagofwords1/bagofwords
All 13 skills in this repoUI Audit
bagofwords1/bagofwords
Exhaustively audit the UI control by control and role by role — enumerate every button, link, and input on a set of pages, write down what each is supposed to do (derived from the handler code and…
Add Connection Type
bagofwords1/bagofwords
Add a new data source / connection type (e.g. An agent skill from bagofwords1/bagofwords.
Add LLM Provider Or Model
bagofwords1/bagofwords
Add a new LLM model to the preset catalog, or a whole new LLM provider — with the mandatory pre-flight verification of model id, pricing, and context window against the provider's official docs.
Docs Update
bagofwords1/bagofwords
Update the product docs at docs.bagofwords.com (Mintlify) with text and fresh screenshots after a user-facing change ships.
Localization
bagofwords1/bagofwords
The locale/i18n architecture of bagofwords — catalogs, resolution order, RTL, backend contracts — and the procedures for adding strings, adding a locale, or translating UI.
QA
bagofwords1/bagofwords
Run a live QA pass over the app — first map all user-facing functionality, then boot the full stack and manually exercise flows with Playwright, recording pass/fail evidence and filing a QA report.
Related
Works with
Categories
Questions about Sandbox Feedback Loop
What does Sandbox Feedback Loop do?
Build a runnable reproduce→fix→verify loop for a bug or feature in a fresh sandbox, and record it as a feedback-loop doc. Sandbox Feedback Loop is an agent skill from bagofwords1/bagofwords. Build a runnable reproduce→fix→verify loop for a bug or feature in a fresh sandbox, and record it as a feedback-loop doc.
When should I use Sandbox Feedback Loop?
Sandbox Feedback Loop fits situations like: investigating a reported bug; validating a root cause; proving a fix works — before and after the change.
How do I install Sandbox Feedback Loop in Claude Code?
Run `npx skills add bagofwords1/bagofwords --skill sandbox-feedback-loop -a claude-code`. Or copy the skill folder (.agents/skills/sandbox-feedback-loop in bagofwords1/bagofwords) into .claude/skills/sandbox-feedback-loop in your project. Claude Code loads it when a task matches its description.
How do I install Sandbox Feedback Loop in Codex?
Run `npx skills add bagofwords1/bagofwords --skill sandbox-feedback-loop -a codex`. Or copy the skill folder (.agents/skills/sandbox-feedback-loop in bagofwords1/bagofwords) into .agents/skills/sandbox-feedback-loop in your project. Codex loads it when a task matches its description.
Can I use Sandbox Feedback Loop 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 bagofwords1/bagofwords --skill sandbox-feedback-loop -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-feedback-loop, .gemini/skills/sandbox-feedback-loop, .github/skills/sandbox-feedback-loop and .opencode/skills/sandbox-feedback-loop in your project.
What does Sandbox Feedback Loop need to run?
Going by SKILL.md and its folder, Sandbox Feedback Loop needs the command-line tools its instructions call (uv, pip and playwright). Our summary lists: Python 3; Docker.
Does Sandbox Feedback Loop access the network?
SKILL.md contains no URLs. Its commands use uv and pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Sandbox Feedback Loop 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 Feedback Loop use?
Sandbox Feedback Loop 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 Sandbox Feedback Loop use?
About 857 tokens (SKILL.md is roughly 3.4k 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 Feedback Loop?
Skills that share tags, products or a category with Sandbox Feedback Loop: RStudio Selenium to Playwright Migration (rstudio/rstudio, 5.1k stars), Cloud Agents Starter (scalar/scalar, 16k stars), Codex E2E Trace Validation (liaohch3/claude-tap, 3.3k stars) and Repro (vaadin/web-components, 582 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Sandbox Feedback Loop?
bagofwords1 (a GitHub organization) maintains it in bagofwords1/bagofwords, which has 458 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on October 8, 2026.
Source: bagofwords1/bagofwords on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.