Borrowing it
Nothing to install: this file belongs to incubateur-ademe/benefriches. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/incubateur-ademe/benefriches/main/.claude/skills/wizard-form/SKILL.mdgit clone --depth 1 https://github.com/incubateur-ademe/benefrichesWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/incubateur-ademe/benefriches/wizard-form)<a href="https://agentmods.dev/skills/incubateur-ademe/benefriches/wizard-form"><img src="https://agentmods.dev/badge/skills/incubateur-ademe/benefriches/wizard-form/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/incubateur-ademe/benefriches/wizard-form"><img src="https://agentmods.dev/badge/skills/incubateur-ademe/benefriches/wizard-form.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00076 | $0.01930 |
| Opus 5 | $0.00038 | $0.00965 |
| Sonnet 5 | $0.00015 | $0.00386 |
| Haiku 4.5 | $0.00008 | $0.00193 |
Grade A, and why
wizard-form scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wizard-Form Engine (apps/web)
One generic algorithm drives every guided, multi-step form in the app — urban & photovoltaic, creation & editing. Each form is a thin definition plugged into a shared engine through an injected lens. Decision record:
docs/adr/0015-extract-wizard-form-engine-via-injected-lens.md.Glossary: Wizard form — one guided flow instance (e.g. urban-create). Context — the eager, guaranteed-present data
buildContextderives from the slice (e.g. the site). Answers — the per-step user input accumulated inWizardFormSubState, keyed byStepId.
Read this before reading the files — it saves you from reverse-engineering the abstraction. Paths below are the source of truth; open them when you need detail.
The one idea: engine + definition, joined by a lens
The engine knows one abstract state shape, generic over <StepId, TAnswers>. It knows nothing about
projects, sites, urban, or PV. A consumer connects its concrete form to the engine by supplying a
WizardFormDefinition whose two key functions are the injected lens:
selectForm(state)— locates this instance'sWizardFormSubStateinside the consumer's slice.buildContext(state)— builds the eager context (the site) handlers read.
That lens is why the same engine + same handler registry serve four live instances: urban-create, urban-update, pv-create, pv-update.
Three layers
L1 shared/core/wizard-form/ generic engine — ZERO domain, no slice/reducer
stepHandler.type.ts handler contract: AnswerStepHandler / InfoStepHandler
wizardForm.reducer.ts the shapes: WizardFormSubState, WizardFormDefinition
wizardForm.actions.ts makeWizardFormActionType(prefix, name) — namespacing
helpers/ the algorithm (pure fns): computeStepChanges, applyStepChanges,
navigateToStep, mutateState, readState, stepsSequence
L2 features/create-project/core/project-form/ shared "reconversion-project-on-a-site" domain
site · stakeholders · soils-carbon · local-authorities · project-name
(used by BOTH project types AND by create + update)
L3 features/create-project/core/{urban-project, renewable-energy}/ one per form type
{type}Steps.ts StepId union + AnswersByStep map (this is TAnswers)
step-handlers/** one pure handler per step
stepHandlerRegistry.ts aggregates them (answerStepHandlers + full nav registry)
{type}Form.reducer.ts add{Type}FormCasesToBuilder(builder, actions, definition)
{type}Form.actions.ts create{Type}FormActions(prefix)
{type}Form.selectors.ts create{Type}FormSelectors(prefix)
Views (feature-owned, shared by create + update):
features/create-project/views/{urban-project, photovoltaic-power-station}/** containers
features/create-project/views/{project-form, .../renewable-energy-form}/ context seam
.../stepToComponent.tsx maps StepId -> the lazy-loaded container
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 13d ago First seen · 143 lines · 76 tokens per session scan A 0c4b011a92b8
wizard-form is a skill published in the GitHub repository incubateur-ademe/benefriches (45 stars, last pushed 4d ago), licensed MIT. It adds 76 tokens to every session and 1,930 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
create-site
Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.
menu-transitions-rtl
Animate react-horizontal-scrolling-menu scrolling and build right-to-left menus: noPolyfill defaults to true since v8, so transitionDuration (default 500), a custom-easing-function transitionBehavior, and per-call ScrollOptions { duration, boundary } on scrollToItem/scrollNext/scrollPrev are silently ignored unless…