What Flows just did
Based on your request to build Add Dark Mode Toggle, Flows created 6 implementation stages and 13 checks.
You asked for: Add a user‑controlled dark mode toggle that instantly updates UI and remembers the choice across sessions.. Flows generated 6 stages because the application requires Use React Context for global theme state; Persist choice in localStorage under the key 'appTheme'; Switch CSS variables via a 'dark' class on a root element. Each stage tells your AI builder what to do, tests whether it actually worked, and gives a repair instruction when it fails. These checks are designed to catch: AI returns placeholder comments like // TODO instead of real code; ThemeContext does not actually read/write localStorage; CSS variables are declared but never applied via class.
Example failure
The form reported success, but no database record was created.
What Flows does
Flows detects the failure, generates a repair instruction, reruns the test, and stores the passing evidence.
Stages — Plan → Build → Test → Fix → Prove → Ship
6 stages · 13 checks · progressive disclosure — open a stage for details
Copy to external builder
Copies a prompt for Claude/Cursor/etc. Records prompt_copied only — not execution, commits, or checks.
Execute through Oort
Requires Sign in with Oort + a provider connection (BYOK). Keys stay on Oort. A model name in the dropdown is not the same as a live connection.
Next
Check off: Can the app import { ThemeProvider } without syn…
Add a proof note on each check — a checkbox alone is weak proof.
Probes & advanced tools are under “More verification tools”. Experience level: Settings.
Project (saved with proof)
Project binding: Unbound — complete project binding before trusting this run · missing repositoryUrl, repositoryStartCommit, environment, stack
More verification tools (probes, timeline, adapters)Show
App persistence (create → read → assert token)
Body template: {"probe":"{{token}}","title":"flows-probe-{{token}}"}. Needs CORS-readable public create/list endpoints (or inconclusive). Badge only when create→read→refresh finds the token (detects false success).
Two-account authorization (User B cannot see/change User A)
Authorization evidence source: Cross-account ownership test (trust level 5/6). These are not equivalent. Unauthenticated probe alone is weaker (source: unauthenticated API probe). Tokens stay in this browser session only — not uploaded to Flows servers.
Generated edge-case tests (review / approve)
- api_probe Submitting the form empty is rejected with a clear error
- api_probe Each required field can be omitted and fails validation
- api_probe Malformed email is rejected
- api_probe Malformed phone is rejected when phone is collected
- api_probe Duplicate submission does not create two records
- api_probe Double-click submit creates only one record
- false_success_probe Failed request does not show success
- browser_automation Refresh during submission does not leave corrupt state
- api_probe Oversized input is rejected
- api_probe Unsafe strings do not execute or break storage
- api_probe Create then refresh still shows the record
- api_probe Edit then refresh keeps the edit
- api_probe Delete then refresh removes the record
- api_probe Nonexistent record ID fails cleanly
- cross_account_probe Cross-user record identifier is rejected
Generated from this route’s signals — you approve; you do not invent security tests.
Content probe (GET body contains text)
In-product content probe reads response text when CORS allows — not full DOM/click automation. Playwright script is optional and external.
Proof strength
thin · 0/100
Heuristic from notes + probes + gates — not a production certification.
Verification adapters
- ● Deploy URL probe · idle
- ● API path probe · idle
- ● Authz probe (unauth → 401/403) · idle
- ● Browser persistence · idle
- ● App persistence (create→read) · idle
- ● Content / body text probe · idle
- ○ In-product Playwright DOM · not embedded (download external script)
Filled circles = available here. Empty = not shipped. Probes are not a production audit. Adapter docs
Step 1 of 6
Not startedCreate Theme Context
Provide global theme state and toggle function.
The app is a React (or similar) SPA with a top‑level App component. No existing theme system.
Flows keeps plan, checks, failures, and next steps connected
Your AI tool writes or changes the code
Repository grounds the plan only after inspect
Checks always carry a validation tier
How this plan was created
Plan from project details
Flows creates steps using the goal, requirements, stack, platform, and details you provide.
- Project description
- Selected template / route
- User-entered stack
- Constraints and notes
- Add Dark Mode Toggle
No repository inspection implied. Connect and inspect a codebase to ground steps in real files.
Codebase access
Checking GitHub…
Or paste a repository URL manually
Use these instructions in Claude, ChatGPT, Cursor, Emergent, or another builder.
Create a new file src/theme/ThemeContext.{js,tsx} that: 1. Imports createContext, useState, useEffect from React. 2. Defines a ThemeContext via createContext({ theme: 'light', toggleTheme: () => {} }). 3. Exports a ThemeProvider component that: a. Initializes theme state from localStorage key 'appTheme' (fallback 'light'). b. Provides toggleTheme that switches between 'light' and 'dark', updates state, and writes the new value to localStorage. c. Wraps its children with ThemeContext.Provider passing { theme, toggleTheme }. 4. Export both ThemeContext and ThemeProvider. Ensure no JSX placeholders; actual functional code only.
Project context
Copies the project goal, technical details, current step, previous progress, and checks so your AI tool understands what it is working on.
Expected after this step
A functional ThemeContext module that can be imported without errors.
Should not happen
- ✕AI returns placeholder comments like // TODO instead of real code
- ✕ThemeContext does not actually read/write localStorage
- ✕CSS variables are declared but never applied via class
- ✕Toggle button does not call the context function
Verify gate — prove this step works before continuing
Do not move on until every check is true. Add proof notes — a checked box alone is weak proof. Checks are manual by default; deploy/API probes live under “More verification tools” and do not auto-check boxes.
Do not continue if…
- !AI returns placeholder comments like // TODO instead of real code
- !ThemeContext does not actually read/write localStorage
- !CSS variables are declared but never applied via class
- !Toggle button does not call the context function
- !Root element class never updates, breaking visual change
- !Persistence test omitted or uses fake data
Repair path — if this step fails
Use the Repair Prompt when a verify gate fails. Loop: Detected → Diagnosed → Repair issued → Changed → Retested → Resolved
Show repair prompt textShow
The generated ThemeContext does not actually persist to localStorage or fails to export. Provide concrete code that fulfills all three checklist items.
Your notes for this step
Definition of Done
Final route-level requirements. Manual checks — separate from per-step verify gates. Completing step gates does not auto-check these. Route completion is not a production-ready claim.