Design Token Inspector
Show which design token produced any value on screen, instead of guessing at computed CSS.
What it adds
A development-only inspector that reports, for a selected element, the tokens behind its colour, spacing, typography, radius, and shadow.
What your agent is told to do
5
What your agent is told to do
5-
1
Find the app's existing token definitions and build the inspector on top of them, so the tool reports the same names the design system publishes rather than a second vocabulary invented for the tool.
-
2
Let a developer point at any element and see, per property, the token name, its resolved value, and where it came from — the element itself, an ancestor, or the theme default.
-
3
Resolve alias chains all the way down and display the whole path, so a surface colour that points at a semantic token that points at a palette primitive shows all three steps rather than only the last.
-
4
Report honestly when a value has no token behind it. An unmatched raw value is the most useful thing the inspector can surface, and it must be labelled as unmatched rather than approximated to the nearest token.
-
5
Do not ship the inspector to production users. Gate it behind a development build or an explicit internal flag, and confirm the code is absent from the production bundle rather than merely unreachable.
Edge cases it handles
7
Edge cases it handles
7- Alias chains must be traced to their source token, and a circular or broken alias must be reported as broken rather than silently rendering the last value it happened to resolve to.
- Inherited values and locally declared values must be visually distinguished — a developer chasing a wrong colour needs to know whether to edit this element or its ancestor.
- The inspector must re-resolve when the active theme or breakpoint changes, because the same element can be driven by different tokens in light and dark, or at different widths.
- Leaving the tool in the production bundle leaks the internal token vocabulary and adds weight for every user; verify its absence in a built artefact, not just in configuration.
- Values produced by calculation or interpolation will not match any token exactly; show the expression and its inputs rather than claiming no token is involved.
- The inspector's own panel must not appear in its own readings, and hovering it must not change what is being inspected.
- Reporting which token is behind a value is this feature's job; deciding that an untokenised value is a defect and failing a check on it belongs to Design Token Linter — the inspector observes, the linter enforces.
Definition of done
8
Definition of done
8- Selecting any element reports the token behind each of its colour, spacing, typography, radius, and shadow values.
- Alias chains are shown in full, from semantic name to source primitive.
- Inherited values are labelled differently from locally declared ones.
- Readings update correctly after a theme change and at every defined breakpoint.
- Values with no matching token are labelled as unmatched rather than rounded to the nearest one.
- The inspector is absent from production builds, verified against the built output.
- The feature matches the existing design system.
- No existing functionality is broken.
Related features
AI Cost Budgets
AI Cost Budgets
Cap what AI features are allowed to spend before the bill arrives.
What it does
Monetary spending limits on AI work, scoped by workspace, feature, and time period, enforced before a run starts.
How it works
- 1 Find every place the app calls a model and route all of them through one accounting point that records estimated and actual spend against a scope. A budget that only covers the chat feature is not a budget.
- 2 Estimate the cost of a run from the size of its input before dispatching it, and refuse anything that would exceed the remaining budget on its own.
- 3 Reserve the estimate against the budget when the run starts, then reconcile to the real usage figures when it finishes, releasing whatever was over-reserved.
Copy the prompt
No account needed
Add this feature to my app:
https://addthisfeature.com/x/ai-cost-budgets
Multi-Model Routing
Multi-Model Routing
Send each AI request to the right model using rules you can read and test.
What it does
A deterministic routing layer that picks a model per request from task type, context size, latency budget, and data sensitivity.
How it works
- 1 Express routing as explicit, ordered rules over inputs the app can measure: task type, estimated context size, latency budget, and the sensitivity classification of the data involved. A rule set that can be read line by line can be reviewed and tested.
- 2 Make routing deterministic. The same inputs must always produce the same route, so a bad output can be reproduced and a rule change can be evaluated. Randomised or load-based selection turns every incident into guesswork.
- 3 Classify data before routing and refuse to route restricted content to any destination not approved for it. This check is a hard block, not a preference, and it must run before the request is assembled.
Copy the prompt
No account needed
Add this feature to my app:
https://addthisfeature.com/x/multi-model-routing
SEO Setup
SEO Setup
Make your app findable — titles, meta, Open Graph, sitemap, robots.
What it does
The baseline SEO and social-preview setup every public app should have, and most skip.
How it works
- 1 Give every public page a unique, descriptive title and meta description. Find the app's layout and add a mechanism for each page to set them.
- 2 Add Open Graph and Twitter Card tags so shared links render a preview instead of a bare URL.
- 3 Generate a sitemap.xml covering every public, indexable page, and a robots.txt pointing at it.
Copy the prompt
No account needed
Add this feature to my app:
https://addthisfeature.com/x/seo-setup
How it works
-
1
Copy the link
Grab the Markdown instruction URL for this feature.
-
2
Give it to your AI
Paste it into Claude Code, Cursor, v0, Lovable — whatever you build with.
-
3
It inspects, then implements
Your agent reads your existing app first, then adds the feature to fit it.
Works with your stack
These instructions are written to adapt. They tell the agent to detect your framework, match your existing design system, and reuse what you already have — rather than assuming a particular stack.
Need it tighter than that? Customize the feature and tell it exactly what you're running.