Agent skill

Builder Smoke Test

by mastra-ai in mastra-ai/mastra

Smoke test the Agent Builder feature branch end-to-end against a hermetic project scaffolded by the skill (linked to the current worktree).

Custom licenceAuto-check: notesTesting & QA

Install Builder Smoke Test

skills CLI
$ npx skills add mastra-ai/mastra --skill builder-smoke-test -a claude-code

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

GitHub CLI
$ gh skill install mastra-ai/mastra builder-smoke-test --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/mastra-ai/mastra.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/builder-smoke-test .claude/skills/builder-smoke-test && 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
builder-smoke-test
GitHub stars
29k
Token cost
~11k tokens
SKILL.md length
3,722 words
Files
28 (incl. scripts, references, assets)
Skills in repo
44
Repo updated
First seen
Licence
Custom licence

At a glance

Smoke test the Agent Builder feature branch end-to-end against a hermetic project scaffolded by the skill (linked to the current worktree).

  • Works in 7 steps: Confirm the project directory. Before… → Read the reference file for each section… → Under --auth on, extract the session… → …
  • Validating the agent-builder feature branch
  • SKILL.md covers ⚠️ Mandatory Test Checklist, Usage, Parameters and Prerequisites, plus 10 more sections
  • Runs TypeScript scripts from its folder; calls bash, pnpm and curl; needs OPENAI_API_KEY and WORKOS_API_KEY

What it does

Builder Smoke Test is an agent skill from mastra-ai/mastra. Smoke test the Agent Builder feature branch end-to-end against a hermetic project scaffolded by the skill (linked to the current worktree). Covers workspace reconciliation, stored agents/skills CRUD, ownership, visibility, stars, registry/library Copy flow, picker allowlists, model policy, RBAC role gating, role impersonation UI, builder defaults, infrastructure diagnostics, channels, and Studio + Agent Builder UI. Trigger when validating the agent-builder feature branch, PRs that touch packages/server…

Its SKILL.md is about 11k tokens, which your agent loads only when the skill is triggered. The skill folder holds 35 other files, including scripts, reference files and assets (for example `assets/template/package.json`, `assets/template/src/mastra/agents/index.ts` and `assets/template/src/mastra/auth.ts`).

It sits in Testing & QA, covering QA and bug reports, Building AI agents and Accounting and bookkeeping. It works with Mastra. The repository describes itself as: Mastra is the modern TypeScript framework for AI-powered applications and agents.

When your agent uses it

  • Validating the agent-builder feature branch
  • PRs that touch packages/server
  • Packages/playground
  • Packages/playground-ui agent-builder routes

Example prompts

  • “/builder-smoke-test”

Requirements

  • Node.js
  • A credential in WORKOS_API_KEY

Workflow steps

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

  1. Confirm the project directory. Before scaffolding, ask the user where they want $PROJECT_DIR to live. Offer the default…
  2. Read the reference file for each section you're about to run.
  3. Under --auth on, extract the session cookie before running any other section. The WorkOS cookie is httpOnly, so curl cannot mint it and…
  4. Seed non-owner data after the server has booted at least once. A fresh scaffold has no skills authored by anyone other than the test user…
  5. Execute the steps — use curl for API checks (with -H "Cookie: $COOKIE" under --auth on), whichever browser tool the harness has wired up…
  6. Record results in the summary table.
  7. Mark the section complete with task_write before moving to the next.

What it can do on your machine

Read from SKILL.md and the folder at commit b98829a. 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

    Ships 1 file in scripts/ (TypeScript, from the files we listed), which the agent can run.

    Shell commands in SKILL.md call:

    • bash
    • pnpm
    • curl

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

  • Network

    No URLs in SKILL.md. Its commands use pnpm and curl, 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:

    • OPENAI_API_KEY
    • WORKOS_API_KEY
    • WORKOS_COOKIE_PASSWORD

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

Context cost

Builder Smoke Test loads about 11k tokens when it runs, and up to ~38k if it reads all its reference files. Until then it costs about 155 tokens; SKILL.md has 3,722 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~155
When it runs · the whole SKILL.md, loaded when a task matches
~11k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~38k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:112
    _KEY value to write into the scaffolded `.env`. If omitted, the scaffold script falls back to `$OPENAI_API_KEY` in the s
  • NoteMentions a .env fileSKILL.md:113
    /localhost:4111/api/auth/callback` into `.env`.
  • NoteMentions a .env fileSKILL.md:132
    different `.env`.
  • NoteMentions a .env fileSKILL.md:199
    ├── .env                                         ← OPENAI_API_KEY (+ AUTH_PROVIDER + WORKOS_* on auth-on)
  • NoteMentions a .env fileSKILL.md:208
    The `.env` is the **only** thing that flips auth on/off — the same `src/mastra/index.ts` runs in both modes. Re-run `scr
  • NoteMentions a .env fileSKILL.md:227
    scaffold.sh` then asserts the resulting `.env` matches `--expect off\|on`.
  • NoteMentions a .env fileSKILL.md:237
    `mastra dev` loads `$PROJECT_DIR/.env` via dotenv and **unconditionally overwrites `process.env`** with whatever's there
  • NoteMentions a .env fileSKILL.md:239
    - **`.env` is the source of truth for the running server.** Inline overrides like `AUTH_PROVIDER= pnpm mastra:dev` are s
  • NoteMentions a .env fileSKILL.md:240
    - **Shell-only vars survive only if `.env` has no entry for the same key.** Re-running `scripts/scaffold.sh` always over
  • NoteMentions a .env fileSKILL.md:241
    erver actually runs in is determined by `.env` alone.** A globally exported `AUTH_PROVIDER=workos` in your shell does NO

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); the scripts in this folder 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 3,722 words (~11,309 tokens).

“End-to-end smoke testing of the Agent Builder feature set against a hermetic project the skill scaffolds at ~/mastra-builder-smoke-tests/builder-smoke (configurable). The project links to the current worktree via pnpm link: overrides, so changes to packages under packages/, stores/, auth/, channels/, observability/…”

— opening of SKILL.md by mastra-ai, Custom licence
name
builder-smoke-test

Read the full SKILL.md on GitHub

Files

SKILL.md and 27 other files (scripts, references, assets) in .claude/skills/builder-smoke-test of mastra-ai/mastra.

  • SKILL.md
  • assets/template/package.json
  • assets/template/src/mastra/agents/index.ts
  • assets/template/src/mastra/auth.ts
  • assets/template/src/mastra/index.ts
  • assets/template/src/mastra/tools/index.ts
  • assets/template/src/mastra/workflows/index.ts
  • assets/template/tsconfig.json
  • references/agents.md
  • references/auth.md
  • references/channels.md
  • references/defaults.md
  • references/favorites.md
  • … and 15 more

Open the folder on GitHubat commit b98829a

Compare with similar skills

Builder Smoke Test 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.

Builder Smoke Test compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Builder Smoke Test this skillmastra-ai/mastra29k—~11kAutomated safety check: NotesCustom licence
Reproucsandman/DashClaw311—~1.5kAutomated safety check: PassMIT
Kit Hellochrisblattman/claudeblattman462—~166Automated safety check: PassMIT
Publishing A New PackageComfy-Org/ComfyUI_frontend2.1k—~1.8kAutomated safety check: PassGPL-3.0
Langgraph Testing Evaluationsoba-labs/langchain-agent-skills107—~2.3kAutomated safety check: PassMIT
Toolifycoreyhaines31/makerskills851—~2.9kAutomated safety check: NotesMIT

Similar skills

  • Repro

    ucsandman/DashClaw

    Turn a bug symptom into a structured, reproducible bug report — summary, environment, exact repro steps, actual vs expected, and evidence (logs, error text, failing route/test) — and then optionally…

    311 GitHub stars~1.5k tokensUpdated yesterday
    Testing & QAAuto-check passed
  • Kit Hello

    chrisblattman/claudeblattman

    Smoke-test skill for the starter kit. An agent skill from chrisblattman/claudeblattman.

    462 GitHub stars~166 tokensUpdated 3 days ago
    Testing & QAAuto-check passed
  • Publishing A New Package

    Comfy-Org/ComfyUI_frontend

    Publishes a new package from this monorepo to npm under @comfyorg and proves it is consumable from another repo.

    2.1k GitHub stars~1.8k tokensUpdated today
    DevelopmentAuto-check passed
  • Langgraph Testing Evaluation

    soba-labs/langchain-agent-skills

    A skill your agent uses when you need to test or evaluate LangGraph/LangChain agents: writing unit or integration tests, generating test scaffolds, mocking LLM/tool behavior, running trajectory…

    107 GitHub stars~2.3k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed
  • Toolify

    coreyhaines31/makerskills

    When you want to integrate an external tool, API, MCP server, or service into a project — the wizard walks you through auth, config, env vars, client wrapper code, example usage, and an optional…

    851 GitHub stars~2.9k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check: notes
  • Plugin Builder

    AIDotNet/NextCoWork

    Author, package, and debug NextCoWork plugins — the single entry point.

    639 GitHub stars~2.4k tokensUpdated yesterday
    DevelopmentAuto-check passed

More from mastra-ai/mastra

All 44 skills in this repo
  • Docs Audit

    mastra-ai/mastra

    Autonomous, report-only documentation review for Mastra docs.

    29k GitHub stars~3k tokensUpdated today
    Auto-check passed
  • Mastra Smoke Test

    mastra-ai/mastra

    Smoke test Mastra projects locally or deploy to staging/production.

    29k GitHub stars~4k tokensUpdated today
    Auto-check: notes
  • React Best Practices

    mastra-ai/mastra

    React performance optimization guidelines from Mastra Engineering.

    29k GitHub stars~1.9k tokensUpdated today
    Auto-check passed
  • Agent Prompt Quality Bar

    mastra-ai/mastra

    Universal quality bar and final audit rubric for any agent system prompt.

    29k GitHub stars~2k tokensUpdated today
    Auto-check passed
  • Coding Agent

    mastra-ai/mastra

    Authoring playbook for building agents that write, edit, review, or refactor code.

    29k GitHub stars~2.3k tokensUpdated today
    Auto-check passed
  • Content Writer Agent

    mastra-ai/mastra

    Authoring playbook for building agents that draft written content — blog posts, marketing copy, social media posts, newsletters, product descriptions, landing pages, or ad copy.

    29k GitHub stars~1.3k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Builder Smoke Test

What does Builder Smoke Test do?

Smoke test the Agent Builder feature branch end-to-end against a hermetic project scaffolded by the skill (linked to the current worktree). Builder Smoke Test is an agent skill from mastra-ai/mastra. Smoke test the Agent Builder feature branch end-to-end against a hermetic project scaffolded by the skill (linked to the current worktree).

When should I use Builder Smoke Test?

Builder Smoke Test fits situations like: validating the agent-builder feature branch; PRs that touch packages/server; packages/playground; packages/playground-ui agent-builder routes.

How do I install Builder Smoke Test in Claude Code?

Run `npx skills add mastra-ai/mastra --skill builder-smoke-test -a claude-code`. Or copy the skill folder (.claude/skills/builder-smoke-test in mastra-ai/mastra) into .claude/skills/builder-smoke-test in your project. Claude Code loads it when a task matches its description.

How do I install Builder Smoke Test in Codex?

Run `npx skills add mastra-ai/mastra --skill builder-smoke-test -a codex`. Or copy the skill folder (.claude/skills/builder-smoke-test in mastra-ai/mastra) into .agents/skills/builder-smoke-test in your project. Codex loads it when a task matches its description.

Can I use Builder Smoke Test 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 mastra-ai/mastra --skill builder-smoke-test -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/builder-smoke-test, .gemini/skills/builder-smoke-test, .github/skills/builder-smoke-test and .opencode/skills/builder-smoke-test in your project.

What does Builder Smoke Test need to run?

Going by SKILL.md and its folder, Builder Smoke Test needs TypeScript for the scripts in its folder, the command-line tools its instructions call (bash, pnpm and curl) and credentials named OPENAI_API_KEY, WORKOS_API_KEY and WORKOS_COOKIE_PASSWORD. Our summary lists: Node.js; A credential in WORKOS_API_KEY.

Does Builder Smoke Test access the network?

SKILL.md contains no URLs. Its commands use curl, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Builder Smoke Test safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Builder Smoke Test use?

Builder Smoke Test 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 Builder Smoke Test use?

About 11k tokens (SKILL.md is roughly 45k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 27k tokens, read only when the agent opens those files.

What are the alternatives to Builder Smoke Test?

Skills that share tags, products or a category with Builder Smoke Test: Repro (ucsandman/DashClaw, 311 stars), Kit Hello (chrisblattman/claudeblattman, 462 stars), Publishing A New Package (Comfy-Org/ComfyUI_frontend, 2.1k stars) and Langgraph Testing Evaluation (soba-labs/langchain-agent-skills, 107 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Builder Smoke Test?

mastra-ai (a GitHub organization) maintains it in mastra-ai/mastra, which has 28,698 GitHub stars. The repository holds 44 skills in this directory. The repository was last updated on October 11, 2026.

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