Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add lukedj78/dev-flow --skill formsgit clone --depth 1 https://github.com/lukedj78/dev-flowWrote 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/lukedj78/dev-flow/forms)<a href="https://agentmods.dev/skills/lukedj78/dev-flow/forms"><img src="https://agentmods.dev/badge/skills/lukedj78/dev-flow/forms/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/lukedj78/dev-flow/forms"><img src="https://agentmods.dev/badge/skills/lukedj78/dev-flow/forms.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 66 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium MCP Rug Pull · line 429 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00226 | $0.08095 |
| Opus 5.5 | $0.00090 | $0.03238 |
| Sonnet 5.5 | $0.00045 | $0.01619 |
| Haiku 4.5 | $0.00023 | $0.00809 |
Grade A, and why
forms 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 1mo 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 — 503 lines — stays where its author put it; the contents beside it link to each section on GitHub.
forms — one toolkit, dirty-gated Save, shared error mapping
This skill governs where the form layer fits in a Next.js 16 App Router app: which hook, which rendering layer, which red flags. It does not teach @tanstack/react-form (or react-hook-form) itself — for the library's own API surface defer to the official docs.
The codebase exposes one shared toolkit at lib/forms/ regardless of which underlying library the project picked. Hook names, rendering layer, and error contract are identical across the two — consumer code looks the same. The choice between TanStack Form (default) and react-hook-form is made once at project scaffold time, written to meta.json#stack.forms, and never mixed.
When this skill applies
- The user asks for a "form", "edit panel", "create dialog", "settings page", "save button".
- Orchestrator (
dev-flow) routes here after scaffolding a route that needs persistence. - The user reaches for
useStateto hold field values, rawuseForm(bypassing the toolkit), hand-rolled dirty tracking, inlinetoast.success/toast.erroron submit, or<form onSubmit>that callsfetch/services directly. - The user asks to audit a Next.js codebase against the form rules.
Contract
This skill follows the dev-flow contract — see references/contracts.md (vendored copy). Key facts:
- Reads
meta.json#stack.framework,stack.nextjs_version,stack.forms,stack.ui. Forframework = "monorepo", reads the equivalent keys understack.monorepo.web.stack.formspicks the state library (selection logic);stack.uipicks the rendering primitives (branching table) — the two are independent and both must be resolved before writing code. - Refuses to apply if any of these is true:
stack.framework ∉ {"next", "monorepo"}— non-Next.js targets are out of scope (RN forms use a different ecosystem; refer the user to the React Native form patterns).stack.nextjs_version != "16"— Next.js 15 and earlier have differentsearchParams, nouse(promise)baseline, norevalidatePath/revalidateTagdefaults. Refuse to apply rather than silently guess.- The project uses Pages Router (
pages/directory exists). App Router only. - The project standardizes on a form library other than
tanstack-formorreact-hook-form(Formik, plain controlled state, etc.). Refuse to mix.
- Appends a
historyentry tometa.jsonfor every scaffold or edit. - Does not bump
phase— forms live inside the implementation phase and don't gate progression.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed f19aedb570bf
- 1mo ago Changed · +2 lines a1eb4c571240
- 1mo ago First seen · 501 lines · 226 tokens per session scan A c8de305011a4
forms is a skill published in the GitHub repository lukedj78/dev-flow (6 stars, last pushed 5d ago), licensed MIT. It adds 226 tokens to every session and 8,095 once invoked, about $0.0009 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
senior-frontend-dev
Provides senior-level frontend development guidance including architecture decisions, performance optimization, accessibility, testing strategies, and modern best practices for React, Next.js, TypeScript, and CSS.
moai-design-tools
Design tool integration specialist covering Figma MCP, Pencil renderer, and Pencil-to-code export. Use when fetching design context from Figma, rendering Pencil designs, or exporting to React/Tailwind code.
writing-react-native-storybook-stories
Create and edit React Native Storybook stories using Component Story Format (CSF). Use when writing .stories.tsx files, adding stories to React Native components, configuring Storybook addons (controls, actions, backgrounds, notes), setting up argTypes, decorators, parameters, or working with portable stories for…
setup-react-native-storybook
Set up Storybook for React Native in Expo, React Native CLI, or Re.Pack projects. Use when adding Storybook to a project, configuring metro.config.js with withStorybook, creating .rnstorybook configuration files, setting up Storybook routes in Expo Router, configuring getStorybookUI, or adding the StorybookPlugin to a…
uniwind
Uniwind — Tailwind CSS v4 styling for React Native. Use when adding, building, or debugging components in a React Native project that uses Uniwind classNames. Covers setup, Metro config, global.css, theming, className props, accent- color props, platform/data/state/responsive variants, CSS variables, custom utilities…
moai-domain-uiux
UI/UX design systems specialist covering accessibility, icons, theming, design tokens, and user experience patterns. Use when working on design systems, WCAG compliance, ARIA patterns, or dark mode theming.