Borrowing it
Nothing to install: this file belongs to ziadeh/react-hook-form-autosave. 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/ziadeh/react-hook-form-autosave/main/.claude/skills/rhf-autosave/SKILL.mdgit clone --depth 1 https://github.com/ziadeh/react-hook-form-autosaveWrote 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/ziadeh/react-hook-form-autosave/rhf-autosave)<a href="https://agentmods.dev/skills/ziadeh/react-hook-form-autosave/rhf-autosave"><img src="https://agentmods.dev/badge/skills/ziadeh/react-hook-form-autosave/rhf-autosave/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/ziadeh/react-hook-form-autosave/rhf-autosave"><img src="https://agentmods.dev/badge/skills/ziadeh/react-hook-form-autosave/rhf-autosave.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00054 | $0.01442 |
| Opus 5.5 | $0.00022 | $0.00577 |
| Sonnet 5.5 | $0.00011 | $0.00288 |
| Haiku 4.5 | $0.00005 | $0.00144 |
Grade A, and why
rhf-autosave 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 2mo 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
react-hook-form-autosave
Drop-in autosave for react-hook-form. Watches dirty fields, debounces, validates, and sends only changed data via a pluggable transport layer.
npm install react-hook-form-autosave
Requires react-hook-form >=7 and react >=18 as peer dependencies.
Minimal Setup
import { useForm } from "react-hook-form";
import { useRhfAutosave, fetchTransport } from "react-hook-form-autosave";
const form = useForm({ defaultValues: { name: "", email: "" } });
const { isSaving, hasPendingChanges } = useRhfAutosave({
form,
transport: fetchTransport("/api/save", { method: "PATCH" }),
config: { debounceMs: 600 },
});
Core Concepts
The library is built around three pillars: a pluggable Transport layer for saving, a Validation strategy that gates saves, and a Baseline tracker that diffs dirty fields against the last-known server state.
Transport
A transport is (payload, ctx?) => Promise<{ ok: true } | { ok: false, error: Error }>.
| Transport | Use case |
|---|---|
fetchTransport(url, opts?) |
REST API |
serverActionTransport(action, opts?) |
Next.js Server Actions |
trpcTransport(mutation) |
tRPC |
Custom transport:
const myTransport: Transport = async (payload) => {
try {
await myApi.save(payload);
return { ok: true };
} catch (e) {
return { ok: false, error: e as Error };
}
};
Wrap any transport with retry: withRetry(transport, { maxRetries: 3, baseDelayMs: 1000 }).
Validation
Control via validateBeforeSave: "payload" (default, changed fields only), "all" (full form), or "none" (skip).
Key Mapping & Payload Transform
// Rename keys (camelCase → snake_case)
keyMap: { fullName: "full_name" }
// Transform entire payload
mapPayload: (payload) => ({ data: payload, updatedAt: Date.now() })
// Select specific fields
selectPayload: (values, dirtyFields) => ({ name: values.name })
Undo / Redo
const { undo, redo, canUndo, canRedo, undoLastSave } = useRhfAutosave({
form,
transport,
undo: { enabled: true, hotkeys: true },
});
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.
- 2mo ago First seen · 179 lines · 54 tokens per session scan A 5055ded83e51
rhf-autosave is a skill published in the GitHub repository ziadeh/react-hook-form-autosave (12 stars, last pushed 4mo ago), licensed MIT. It adds 54 tokens to every session and 1,442 once invoked, about $0.0002 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 2026-08-30.
rhf-autosave compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| rhf-autosaveziadeh/react-hook-form-autosave | Skill | 12 | 4mo ago | MIT | A | 54 | Claude Code |
| build-ghost-appTryGhost/Ghost | Skill | 56k | yesterday | MIT | A | 44 | Claude Code, Codex |
| chakra-ui-builderchakra-ui/chakra-ui | Skill | 41k | yesterday | MIT | A | 214 | Claude Code, Codex |
| material-ui-tailwindmui/material-ui | Skill | 99k | yesterday | MIT | A | 67 | Claude Code, Codex |
| fuzzy-rankingTanStack/table | Skill | 29k | 4d ago | MIT | A | 62 | Claude Code, Codex |
| r3f-best-practiceszebbern/claude-code-guide | Skill | 4.7k | 3d ago | MIT | A | 74 | Claude Code, Codex |
| git-safetytamagui/tamagui | Skill | 14k | today | MIT | A | 0 | Claude Code |