Borrowing it
Nothing to install: this file belongs to swt-labs/vibe-better-with-claude-code-vbw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/swt-labs/vibe-better-with-claude-code-vbw/main/.claude/skills/running-claude-smoke-tests/SKILL.mdgit clone --depth 1 https://github.com/swt-labs/vibe-better-with-claude-code-vbwWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/swt-labs/vibe-better-with-claude-code-vbw/running-claude-smoke-tests)<a href="https://agentmods.dev/skills/swt-labs/vibe-better-with-claude-code-vbw/running-claude-smoke-tests"><img src="https://agentmods.dev/badge/skills/swt-labs/vibe-better-with-claude-code-vbw/running-claude-smoke-tests/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/swt-labs/vibe-better-with-claude-code-vbw/running-claude-smoke-tests"><img src="https://agentmods.dev/badge/skills/swt-labs/vibe-better-with-claude-code-vbw/running-claude-smoke-tests.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00076 | $0.03274 |
| Opus 5 | $0.00038 | $0.01637 |
| Sonnet 5 | $0.00015 | $0.00655 |
| Haiku 4.5 | $0.00008 | $0.00327 |
Grade A, and why
running-claude-smoke-tests scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- running-ccr-smoke-tests — 91% identical, 127 lines differ
How it starts
The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Running Claude Code smoke tests
Use this skill when validating VBW behavior with plain Claude Code so future issue-fix runs do not have to rediscover the local CLI entrypoint, the consumer repo path, or the provenance checks. This is the plain-Claude counterpart to the CCR smoke-test workflow: keep the worktree and provenance rules the same, but replace ccr code with claude.
Core rule
- Do not run the smoke test with the VBW plugin repo or plugin worktree as the working directory.
- Do not run the smoke test directly in the base consumer repo checkout.
- Create or reuse a disposable consumer smoke worktree and run
claudethere, or use a sandbox repo when the real consumer repo cannot exercise the flow. - Use the candidate VBW checkout only as
--plugin-dir. - If the smoke needs installed skill fixtures, seed them only under the consumer repo's
.claude/skills/<skill>/tree or the global Claude configskills/directory after sourcingscripts/resolve-claude-dir.shand using${CLAUDE_DIR}. Do not use.agents/or.pi/as positive fixtures. - When documenting results, say: "smoke-tested from a consumer smoke worktree or sandbox while loading the candidate plugin checkout via
--plugin-dir". - If the transcript path encodes the plugin repo or the base consumer repo checkout instead of the consumer smoke worktree or sandbox, treat the smoke result as suspect until proven otherwise.
Expected inputs
- Candidate plugin checkout path, usually the current VBW worktree under test.
- Preferred consumer repo path, resolved from the VBW checkout with:
bash scripts/resolve-debug-target.sh repo
- Smoke worktree label such as
smoke-fix-issue-502orsmoke-skill-audit. - Optional sandbox path such as
/tmp/vbw-skill-smoke-<issue>for phase-routed flows the real consumer repo cannot exercise.
Location roles
Keep these four locations distinct throughout the run:
- Candidate plugin checkout — the VBW repo checkout under test. Pass this path only through
--plugin-dir. - Consumer repo — the real target repo used to resolve the testing target and create or remove the smoke worktree. Do not run
claudefrom this checkout. - Consumer smoke worktree — the disposable worktree created from the consumer repo. This is the real cwd for consumer-repo smoke tests.
- Sandbox repo — a temporary repo used only when the consumer repo cannot exercise the required phase-routed flow.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 265 lines · 76 tokens per session scan A 3f5a99a4ae01
running-claude-smoke-tests is a skill published in the GitHub repository swt-labs/vibe-better-with-claude-code-vbw (79 stars, last pushed 2mo ago), licensed MIT. It adds 76 tokens to every session and 3,274 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…
pyats-dynamic-test
Generate and execute deterministic pyATS aetest validation scripts - interface state, OSPF neighbors, BGP paths, ping matrices, and custom compliance tests. Use when writing a network test, validating post-change state, running pass/fail checks, or building automated regression tests.
test-loop
Plan, generate, and heal an executable E2E test suite from approved acceptance criteria (web and mobile).
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…