New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Sandbox Feedback Loop

by bagofwords1 in bagofwords1/bagofwords

Boot a full local Bag of Words sandbox (backend + frontend + real LLM), drive it end-to-end through the UI with Playwright, and verify behavior at the DB / backend-log / HTTP layers.

Custom licenceAuto-check passedTesting & QA

Install Sandbox Feedback Loop

skills CLI
$ npx skills add bagofwords1/bagofwords --skill sandbox-feedback-loop -a claude-code

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

GitHub CLI
$ gh skill install bagofwords1/bagofwords sandbox-feedback-loop --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/bagofwords1/bagofwords.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/sandbox-feedback-loop .claude/skills/sandbox-feedback-loop && 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/

Facts

Skill name
sandbox-feedback-loop
GitHub stars
459
Token cost
~2.8k tokens
SKILL.md length
1,287 words
Files
1
Skills in repo
13
Repo updated
First seen
Licence
Custom licence

At a glance

Boot a full local Bag of Words sandbox (backend + frontend + real LLM), drive it end-to-end through the UI with Playwright, and verify behavior at the DB / backend-log / HTTP layers.

  • Works in 6 steps: Boot the sandbox → Seed a user + org + LLM (one-time per… → Drive the chat UI → …
  • A change needs real e2e validation (agent context
  • SKILL.md covers 1. Boot the sandbox, 2. Seed a user + org + LLM…, 3. Drive the chat UI and 4. Agents (data sources) and…, plus 3 more sections
  • Calls uv, yarn and python; reaches api.anthropic.com; needs ANTHROPIC_KEY and BOW_ENCRYPTION_KEY

What it does

Sandbox Feedback Loop is an agent skill from bagofwords1/bagofwords. Boot a full local Bag of Words sandbox (backend + frontend + real LLM), drive it end-to-end through the UI with Playwright, and verify behavior at the DB / backend-log / HTTP layers. Use when a change needs real e2e validation (agent context, chat flows, file uploads, LLM behavior) rather than just unit tests.

Its SKILL.md is about 2.8k 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 End-to-end testing, Unit testing and File uploads and storage. It works with 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

  • A change needs real e2e validation (agent context
  • LLM behavior) rather than just unit tests

Example prompts

  • “/sandbox-feedback-loop”

Requirements

  • Python 3
  • Node.js
  • Docker
  • A credential in ANTHROPIC_KEY
  • A credential in BOW_ENCRYPTION_KEY

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Boot the sandbox
  2. Seed a user + org + LLM (one-time per fresh DB)
  3. Drive the chat UI
  4. Agents (data sources) and their file libraries — API is fine for setup
  5. Verify at the lower layers
  6. Iterate

What it can do on your machine

Read from SKILL.md and the folder at commit f227059. 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:

    • uv
    • yarn
    • python
    • bash
    • npm

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • api.anthropic.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • ANTHROPIC_KEY
    • BOW_ENCRYPTION_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Sandbox Feedback Loop loads about 2.8k tokens when it runs. Until then it costs about 83 tokens; SKILL.md has 1,287 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~83
When it runs · the whole SKILL.md, loaded when a task matches
~2.8k

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 1,287 words (~2,829 tokens).

“Boot the app, drive it through the real UI, verify at every layer. Iterate.”

— opening of SKILL.md by bagofwords1, Custom licence
name
sandbox-feedback-loop

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .claude/skills/sandbox-feedback-loop of bagofwords1/bagofwords.

Open the folder on GitHubat commit f227059

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.

Sandbox Feedback Loop compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Sandbox Feedback Loop this skillbagofwords1/bagofwords459—~2.8kAutomated safety check: PassCustom licence
Control UI E2Eopenclaw/openclaw392k—~2.9kAutomated safety check: PassMIT
VerifyGnathonic/mokuro-reader209—~724Automated safety check: PassGPL-3.0
Svelte Testingspences10/sveltest113—~579Automated safety check: PassMIT
Playwright Testingchongdashu/vibejam-starter-pack149—~2.1kAutomated safety check: PassNone
Ha Frontend Testinghome-assistant/frontend5.7k—~1.7kAutomated safety check: PassApache-2.0

Similar skills

  • Control UI E2E

    openclaw/openclaw

    A skill your agent uses when designing, testing, fixing, or extending the OpenClaw Control UI GUI, including UI stress-test galleries with feedback inputs, Vitest + Playwright end-to-end checks…

    392k GitHub stars~2.9k tokensUpdated today
    Testing & QAAuto-check passed

  • Verify

    Gnathonic/mokuro-reader

    Verify reader features end-to-end by importing a synthetic volume through the real upload modal and driving the reader with Playwright.

    209 GitHub stars~724 tokensUpdated yesterday
    Testing & QAAuto-check passed

  • Svelte Testing

    spences10/sveltest

    Fix and create Svelte 5 tests with vitest-browser-svelte and Playwright.

    113 GitHub stars~579 tokensUpdated today
    Testing & QAAuto-check passed

  • Playwright Testing

    chongdashu/vibejam-starter-pack

    Plan, implement, and debug frontend tests: unit/integration/E2E/visual/a11y.

    149 GitHub stars~2.1k tokensUpdated 5 mo ago
    Testing & QAAuto-check passed

  • Ha Frontend Testing

    home-assistant/frontend

    Home Assistant frontend testing and validation workflow. An agent skill from home-assistant/frontend.

    5.7k GitHub stars~1.7k tokensUpdated today
    Testing & QAAuto-check passed

  • Playwright Testing

    chongdashu/vibejam-starter-pack

    Plan, implement, and debug frontend tests: unit/integration/E2E/visual/a11y.

    149 GitHub stars~2.2k tokensUpdated 5 mo ago
    Testing & QAAuto-check passed

More from bagofwords1/bagofwords

All 13 skills in this repo

  • UI 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…

    459 GitHub stars~2.9k tokensUpdated today
    Auto-check passed

  • Add Connection Type

    bagofwords1/bagofwords

    Add a new data source / connection type (e.g. An agent skill from bagofwords1/bagofwords.

    459 GitHub stars~2.3k tokensUpdated today
    Auto-check passed

  • 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.

    459 GitHub stars~1.3k tokensUpdated today
    Auto-check passed

  • Docs Update

    bagofwords1/bagofwords

    Update the product docs at docs.bagofwords.com (Mintlify) with text and fresh screenshots after a user-facing change ships.

    459 GitHub stars~746 tokensUpdated today
    Auto-check passed

  • 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.

    459 GitHub stars~1.5k tokensUpdated today
    Auto-check passed

  • 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.

    459 GitHub stars~824 tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Sandbox Feedback Loop

What does Sandbox Feedback Loop do?

Boot a full local Bag of Words sandbox (backend + frontend + real LLM), drive it end-to-end through the UI with Playwright, and verify behavior at the DB / backend-log / HTTP layers. Sandbox Feedback Loop is an agent skill from bagofwords1/bagofwords. Boot a full local Bag of Words sandbox (backend + frontend + real LLM), drive it end-to-end through the UI with Playwright, and verify behavior at the DB / backend-log / HTTP layers.

When should I use Sandbox Feedback Loop?

Sandbox Feedback Loop fits situations like: A change needs real e2e validation (agent context; LLM behavior) rather than just unit tests.

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 (.claude/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 (.claude/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, yarn, python, bash and npm) and credentials named ANTHROPIC_KEY and BOW_ENCRYPTION_KEY. Our summary lists: Python 3; Node.js; Docker; A credential in ANTHROPIC_KEY; A credential in BOW_ENCRYPTION_KEY.

Does Sandbox Feedback Loop access the network?

SKILL.md names 1 domain. In commands or code: api.anthropic.com; the agent is likely to contact it when it follows the instructions. 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 2.8k tokens (SKILL.md is roughly 11k 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: Control UI E2E (openclaw/openclaw, 392k stars), Verify (Gnathonic/mokuro-reader, 209 stars), Svelte Testing (spences10/sveltest, 113 stars) and Playwright Testing (chongdashu/vibejam-starter-pack, 149 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 459 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on October 10, 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.