Component Usage Documentation
Put the rules for using a component next to the component, where they get read.
What it adds
Usage documentation attached to each shared component covering intended use, variants, accessibility obligations, and the patterns to avoid.
What your agent is told to do
5
What your agent is told to do
5-
1
Inventory the shared components the app already has and write documentation for the ones that are used in more than one place. A component used once does not need a page; a component used forty times does.
-
2
For each component, state what it is for, which variants exist and when each applies, what the consumer is responsible for accessibility-wise, and which props or slots are load-bearing.
-
3
Include at least one realistic example per variant, using the app's own copy and data rather than lorem text. An example showing a three-character label hides the wrapping problem that every real usage hits.
-
4
Keep the documentation in the same directory as the component and update it in the same change that alters behaviour, so a reviewer sees a variant added and its documentation missing in one diff.
-
5
Do not write a separate documentation site maintained by hand. A second source of truth drifts within weeks and then actively misleads the people who trust it.
Edge cases it handles
7
Edge cases it handles
7- Examples that are only prose go stale silently. Render the examples from the same code the documentation shows, or run them in the test suite, so a broken example fails a build rather than misleading a reader.
- Every component needs an explicit section on when not to use it and what to reach for instead — a dialog documented without the note that a destructive confirmation belongs to the confirmation pattern will be used for both.
- Documentation must be versioned alongside the implementation, so a consumer pinned to an older release reads the rules that actually applied then.
- Realistic examples must include the awkward states: long labels, missing optional data, right-to-left text, and the loading and error variants, not just the happy path.
- A component that has been deprecated must say so at the top with its replacement named, rather than quietly remaining as valid-looking guidance.
- Accessibility notes must say who owns what — if the component renders the control but the consumer supplies the label, the documentation must state that the label is not optional.
- Screenshots go out of date faster than anything else. Prefer live rendered examples, and if a screenshot is unavoidable, note what it is showing so a stale one is obvious.
Definition of done
8
Definition of done
8- Every component used in more than one place has usage documentation beside its implementation.
- Each documented component names its variants, its intended use, and at least one case where it is the wrong choice.
- Examples render from real code and fail the build when the component's interface changes.
- Accessibility responsibilities are split explicitly between the component and its consumer.
- Documentation ships in the same change as the behaviour it describes.
- Deprecated components carry a visible notice naming their replacement.
- 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
Model Selection
Model Selection
Let each AI task run on the model that suits its quality, speed, and cost needs.
What it does
A per-task model choice, drawn from the models the app already has configured, with capability filtering and safe defaults.
How it works
- 1 Enumerate the models the app already has access to and record what each one can actually do: context capacity, whether it can return the structured output the task requires, whether it supports the tools the task calls, and its relative cost and speed.
- 2 Offer only the models that satisfy the task's requirements. A task that needs structured output must not list a model that cannot reliably produce it, because the failure appears later as malformed responses rather than as an unavailable option.
- 3 Store the choice against the specific task, not as one global setting. A single default forces a summarisation task and a classification task onto the same tier when they have opposite needs.
Copy the prompt
No account needed
Add this feature to my app:
https://addthisfeature.com/x/model-selection
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.