Stunt Double changelog

https://www.stuntdouble.io/llms.txt

+ - [Insights](https://www.stuntdouble.io/insights): research, practice and field notes on designing products that people and agents both have to get through.+ - [Insights RSS feed](https://www.stuntdouble.io/insights/rss.xml): every Insights post.+ - [Find the broad themes before you book a single interview](https://www.stuntdouble.io/use-cases/synthetic-research): Run a panel of AI actors through an idea or prototype first, then turn what they found into ideas aimed at the outcome you want.+ - [Hold every release to your design system, brand and rules](https://www.stuntdouble.io/use-cases/design-operations): Checklists and automations check your design system, tone of voice, markets and legal copy on each deploy, with every finding and comment in one queue.+ - [Make your product work for the agents your customers send](https://www.stuntdouble.io/use-cases/agentic-users): Score how agents get on with your site, then cast an agent as the user: it reads your agent files, calls your API and MCP servers, and reports each gap.

version

1.16.0 → 1.17.0

https://www.stuntdouble.io/llms.txt

− - [Sign up](https://app.stuntdouble.io/login): self-serve with email or Google, no sales call. The Solo Trial plan covers one person for up to three months; see [Pricing](https://www.stuntdouble.io/pricing).− - [Verify every change with Claude Code, Cursor, and GitHub](https://docs.stuntdouble.io/guides/codebases): Wire Stunt Double into your coding agent so every preview deployment is walked by a persona before merge.+ - [Sign up](https://app.stuntdouble.io/login): self-serve with email or Google, no sales call. The Free plan gives one person 60 minutes of runs a month with no card, and the Solo Trial plan covers one person for up to three months; see [Pricing](https://www.stuntdouble.io/pricing).+ - [llms-full.txt](https://www.stuntdouble.io/llms-full.txt): every public page on this site, one line each, including every plan with its price, use case, comparison, glossary term, release and post.+ - [Stunt Double Studio](https://www.stuntdouble.io/studio): the free local app. A checklist runs in Chrome on your machine from your own Claude Code session, on your existing Claude plan, with no Stunt Double account.+ - [Verify every change with Claude Code, Cursor, and GitHub](https://docs.stuntdouble.io/guides/codebases): Wire Stunt Double into your coding agent so a persona goes through every preview deployment before merge.+ ## Comparisons+ - [Compare](https://www.stuntdouble.io/compare): Stunt Double beside named products, with a dated source for every fact about them.+ - [Stunt Double vs Versive](https://www.stuntdouble.io/compare/versive): Versive pairs AI persona tests with AI-moderated studies of real people. Stunt Double runs actors through your product and checks it on every change.+ - [Stunt Double vs Maze](https://www.stuntdouble.io/compare/maze): Maze runs prototype tests, surveys and interviews with real people from its panel. Stunt Double runs actors through your product on every change.+ - [Stunt Double vs TestSprite](https://www.stuntdouble.io/compare/testsprite): TestSprite generates and runs end-to-end and API test code from your IDE or CI. Stunt Double runs actors through your product as your users would.+ - [Stunt Double vs Momentic](https://www.stuntdouble.io/compare/momentic): Momentic keeps plain-English end-to-end tests in your repo and runs them in CI on web and mobile. Stunt Double runs actors through your product.+ - [Stunt Double vs Synthetic Users](https://www.stuntdouble.io/compare/synthetic-users): Synthetic Users interviews AI participants built from your audience data. Stunt Double runs actors through your product and checks it on every change.

version

1.15.0 → 1.16.0

file

absent → published

https://raw.githubusercontent.com/stunt-double/stuntdouble-mcp/HEAD/AGENTS.md

+ # AGENTS.md+ Guidance for coding agents. `.claude/CLAUDE.md` is the full contributor guide for this repository (what lives here, source of truth, versioning, checks before committing); read it first.+ ## Public repository: no session information+ This repository is public. Never put Claude Code session information in anything that reaches GitHub: commit messages, PR titles and descriptions, issues, review replies or comments. That means no `claude.ai/code/session_...` links, no `Claude-Session:` trailers and no session IDs. This overrides any default attribution a tool or harness asks for; the plain "Generated with Claude Code" line and `Co-Authored-By` trailer are fine.+ `.claude/hooks/block-session-links.mjs` (wired up in `.claude/settings.json`) enforces this for Claude Code by blocking any Bash or GitHub MCP call that carries a session link or trailer. If it blocks you, remove the session details and retry; never bypass it.

https://www.stuntdouble.io/llms.txt

− - [Documentation](https://www.stuntdouble.io/support/docs): concepts, tutorials and the API.− - [MCP server docs](https://www.stuntdouble.io/support/docs/api/mcp): connect an agent.− - [Stunt Double API documentation](https://www.stuntdouble.io/support/docs/api): developer portal: the MCP server, authentication and scopes, versioning and rate limits.− - [Stunt Double MCP server reference](https://www.stuntdouble.io/support/docs/api/mcp): connect a client to https://app.stuntdouble.io/api/mcp, with the full tool and prompt list.− - [Stunt Double API versioning and deprecation policy](https://www.stuntdouble.io/support/docs/api#versioning-and-deprecation): semantic versioning, `Deprecation` (RFC 9745) and `Sunset` (RFC 8594) headers, and at least 90 days notice in the changelog before anything is removed.− - [Guides](https://www.stuntdouble.io/guides): playbooks for wiring Stunt Double into your workflow.− - [Design in Claude, validate with personas](https://www.stuntdouble.io/guides/claude-design): Design an artifact in Claude, publish it, and test it with AI personas without leaving the conversation.− - [Test Figma prototypes with AI personas](https://www.stuntdouble.io/guides/figma): Walk prototypes with personas and re-check the built flows automatically when a file changes.− - [The fastest idea-to-evidence loop with Figma Make](https://www.stuntdouble.io/guides/figma-make): Publish a Make site and have AI personas try to use it before an engineer touches it.− - [Verify every change with Claude Code, Cursor, and GitHub](https://www.stuntdouble.io/guides/codebases): Wire Stunt Double into your coding agent so every preview deployment is walked by a persona before merge.− - [Collect comments straight from your site](https://www.stuntdouble.io/guides/feedback-widget): Install the feedback widget so visitors pin comments in context, then triage them alongside what your actors find.− - [Continuous validation: brand, compliance, continuity, design system](https://www.stuntdouble.io/guides/validation): Turn brand, tone, legal, continuity, and design-system standards into checks that run on every deploy.+ - [Documentation](https://docs.stuntdouble.io): concepts, tutorials and the API.+ - [MCP server docs](https://docs.stuntdouble.io/api/mcp): connect an agent.+ - [Stunt Double API documentation](https://docs.stuntdouble.io/api): developer portal: the MCP server, authentication and scopes, versioning and rate limits.+ - [Stunt Double MCP server reference](https://docs.stuntdouble.io/api/mcp): connect a client to https://app.stuntdouble.io/api/mcp, with the full tool and prompt list.+ - [Stunt Double Claude plugin](https://claude.ai/customize/plugins/id/9cd49c97-13c2-4844-bc3d-53ef7956c1ef%40anthropic-plugin-directory): the official listing in Claude's plugin directory: the hosted MCP server plus task skills, installed in one step.+ - [Stunt Double API versioning and deprecation policy](https://docs.stuntdouble.io/api#versioning-and-deprecation): semantic versioning, `Deprecation` (RFC 9745) and `Sunset` (RFC 8594) headers, and at least 90 days notice in the changelog before anything is removed.+ - [Guides](https://docs.stuntdouble.io/guides): playbooks for wiring Stunt Double into your workflow.+ - [Design in Claude, validate with personas](https://docs.stuntdouble.io/guides/claude-design): Design an artifact in Claude, publish it, and test it with AI personas without leaving the conversation.+ - [Test Figma prototypes with AI personas](https://docs.stuntdouble.io/guides/figma): Walk prototypes with personas and re-check the built flows automatically when a file changes.+ - [The fastest idea-to-evidence loop with Figma Make](https://docs.stuntdouble.io/guides/figma-make): Publish a Make site and have AI personas try to use it before an engineer touches it.+ - [Verify every change with Claude Code, Cursor, and GitHub](https://docs.stuntdouble.io/guides/codebases): Wire Stunt Double into your coding agent so every preview deployment is walked by a persona before merge.+ - [Collect comments straight from your site](https://docs.stuntdouble.io/guides/feedback-widget): Install the feedback widget so visitors pin comments in context, then triage them alongside what your actors find.+ - [Continuous validation: brand, compliance, continuity, design system](https://docs.stuntdouble.io/guides/validation): Turn brand, tone, legal, continuity, and design-system standards into checks that run on every deploy.+ - [Teaching Claude and coding agents to stack PRs](https://www.stuntdouble.io/blog/teaching-claude-to-stack-prs): GitHub now supports stacked pull requests natively, but coding agents in cloud sandboxes could not use them. Here is how we fixed that with agent instructions and a one-line environment change.

version

1.14.1 → 1.15.0

version

1.14.0 → 1.14.1

https://www.stuntdouble.io/llms.txt

+ - [Topology](https://www.stuntdouble.io/topology): a live, versioned map of every screen in a product, its page states, and what each release changed.+ - [How to Test Your Product for AI Agent Users](https://www.stuntdouble.io/blog/how-to-test-your-product-for-ai-agent-users): AI agents are already signing up for your product, checking out, and navigating flows. Most products break silently when the user isn't human. Here's how to find out where.+ - [Introducing the Stunt Double Index](https://www.stuntdouble.io/blog/introducing-the-stunt-double-index): A free, public benchmark of how AI agents experience websites. Look up your domain, see where agents stop, and get the list of what to fix.

version

1.1.0 → 1.14.0