{"name":"\/claude-test","slug":"claude-test","family":"slash","title":"Slash commands","noun":"slash command","description":"New built-in 'Claude Test' plugin runs plain-language specs against your local dev server in a real browser and reports PASS\/FAIL","description_source":"entry","described_by":{"version":"2.1.274","anchor":"new-built-in-claude-test-plugin-for-browser-based-spec-tes"},"presence":{"first_seen":null,"removed_in":null,"in_current_build":false,"newest_mined":"2.1.319","builds":0,"mined_builds":159,"first_cited":{"version":"2.1.293","released_at":"2026-10-07 17:18:04","spans":2}},"aliases":[],"entries":[{"version":"2.1.310","anchor":"claude-test-progress-panel-added-tied-to-a-built-in-claude","heading":"A Claude Test progress panel for app testing appears in the terminal","line":"Claude Code includes a Claude Test panel showing app start-up, each test's pass, fail or blocked mark, a progress bar and time left","released_at":"2026-10-23 21:20:46","reason":"found in this entry's text"},{"version":"2.1.307","anchor":"claude-test-helper-messages-added","heading":"Claude Test tells you to type \/claude-test when its browser helper is not ready","line":"When the browser helper is not ready, Claude Code now says Claude Test did not run and asks you to type `\/claude-test`","released_at":"2026-10-21 20:47:18","reason":"named in this entry, found in this entry's text"},{"version":"2.1.305","anchor":"claude-test-plugin-browser-helper-environment-sanitising","heading":"Claude Test's browser helper ignores risky project environment settings","line":"The browser helper behind `\/claude-test` runs with a cleaned environment that ignores proxy, `NODE_OPTIONS` and `LD_PRELOAD` values from project settings","released_at":"2026-10-20 19:29:36","reason":"found in this entry's text, named in this entry"},{"version":"2.1.304","anchor":"claude-test-plugin-checks-agents-and-renders-a-pane","heading":"Claude Test now checks its test agents are loaded and shows a progress pane","line":"\/claude-test now stops with a clear message if its test agents are not loaded, and shows a pane where test progress will appear later","released_at":"2026-10-19 19:47:15","reason":"found in this entry's text, named in this entry"},{"version":"2.1.304","anchor":"claude-test-reports-a-new-diskless-failure","heading":"Claude Test explains why it can't start in sessions without a disk","line":"Claude Test now says its browser helper can't run in a session with no disk of its own, instead of a general error","released_at":"2026-10-19 19:47:15","reason":"found in this entry's text"},{"version":"2.1.302","anchor":"claude-test-browser-helper-stops-itself-when-login-or-plan-c","heading":"Claude Test's browser helper switches off when your login or plan changes","line":"If your Claude Code login or plan changes, or cannot be checked, Claude Test stops its browser helper and tells you how to restart","released_at":"2026-10-16 16:48:28","reason":"found in this entry's text"},{"version":"2.1.293","anchor":"claude-test-plugin-gating-and-claude-test-messages","heading":"New messages for the built-in Claude Test feature and \/claude-test","line":"Claude Test gains sign-in-dependent access and messages for when it is still loading or its browser helper failed to load","released_at":"2026-10-07 17:18:04","reason":"found in this entry's text, named in this entry"},{"version":"2.1.286","anchor":"claude-test-launch-failure-message-replaces-bundled-skill-as","heading":"Error message for when Claude Test cannot connect its browser helper","line":"Claude Code contains an error saying Claude Test did not start because its browser helper did not connect, with steps to try","released_at":"2026-09-30 17:14:38","reason":"found in this entry's text"},{"version":"2.1.274","anchor":"new-built-in-claude-test-plugin-for-browser-based-spec-tes","heading":"New built-in \"Claude Test\" plugin for browser-based spec testing","line":"New built-in 'Claude Test' plugin runs plain-language specs against your local dev server in a real browser and reports PASS\/FAIL","released_at":"2026-09-16 22:36:09","reason":"named in this entry, found in this entry's text"}],"entries_total":9,"docs":[],"docs_total":0,"gates":[],"related":[{"name":"\/claude-api","slug":"claude-api","description":"**[Skill](\/docs\/en\/skills#bundled-skills).** Load [Claude API](https:\/\/platform.claude.com\/docs\/en\/api\/overview) and [Managed Agents](https:\/\/platform.claude.com\/docs\/en\/managed-agents\/overview) reference material for your project's language. Also activates automatically when your code imports `anthropic` or `@anthropic-ai\/sdk`. Run `migrate` to update existing Claude API code to a newer model. Run `upgrade` to move your project's Anthropic SDK dependency across a major version, currently the Python `anthropic` package from 0.x to 1.x. Run `managed-agents-onboard` for a walkthrough that creates a new Managed Agent. Run `prompt-audit` to flag instructions written for older models in your prompts, skills, and tool descriptions and propose fixes as a diff. Run `cost-optimize` to profile where your project's Claude API spend goes and propose savings from options such as prompt caching, trimming unneeded input and output tokens, batch processing, effort, and model choice, one change at a time. Run `build-eval` to build an eval set for your Claude-powered app, and `hillclimb` to iteratively improve the app against an existing eval. The `prompt-audit` subcommand requires Claude Code v2.1.221 or later, `upgrade` requires v2.1.236 or later, `cost-optimize` requires v2.1.247 or later, and `build-eval` and `hillclimb` require v2.1.259 or later"},{"name":"\/claude-in-chrome","slug":"claude-in-chrome","description":"When CLAUDE_CODE_DISABLE_CFC_PROMPT is set, Claude Code now tells host apps like the VS Code extension, which then drop their own browser instructions"}],"url":"https:\/\/changelogs.core-directive.com\/reference\/slash\/claude-test","family_url":"https:\/\/changelogs.core-directive.com\/reference\/slash.json"}