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 LazyAGI/LazyMind --skill ui-safe-form-patternsgit clone --depth 1 https://github.com/LazyAGI/LazyMindWrote 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/lazyagi/lazymind/ui-safe-form-patterns)<a href="https://agentmods.dev/skills/lazyagi/lazymind/ui-safe-form-patterns"><img src="https://agentmods.dev/badge/skills/lazyagi/lazymind/ui-safe-form-patterns/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/lazyagi/lazymind/ui-safe-form-patterns"><img src="https://agentmods.dev/badge/skills/lazyagi/lazymind/ui-safe-form-patterns.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 | $0.00050 | $0.00505 |
| Opus 5.5 | $0.00020 | $0.00202 |
| Sonnet 5.5 | $0.00010 | $0.00101 |
| Haiku 4.5 | $0.00005 | $0.00051 |
Grade A, and why
ui-safe-form-patterns 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI Safe Form Patterns
Use this skill to build forms that are both secure and dependable in real user conditions.
When to use
- Creating new forms or refactoring existing form logic.
- Hardening forms that process credentials, PII, money, or privileged actions.
- Fixing flaky submission flows and duplicate-submit bugs.
Reliability and safety baseline
- Validate on both client and server.
- Treat client validation as UX, not security control.
- Normalize input before validation when format ambiguity is common.
- Prevent duplicate submissions with in-flight state and idempotent APIs.
- Use clear loading, success, retry, and failure states.
- Never leak secrets or raw backend traces in UI errors.
Implementation workflow
- Define schema and constraints per field, including max lengths and allowed character sets.
- Build controlled input handling with immediate low-cost validation and deferred heavy checks.
- Sanitize or encode displayed user-provided content in previews and confirmation screens.
- Add submit lock, timeout handling, and cancel or retry behavior where relevant.
- Map backend errors into safe user-facing messages without exposing internals.
- Add tests for invalid input, race conditions, and repeated clicks.
Sensitive field rules
- Password fields: enforce minimum policy and avoid logging or analytics capture.
- Email and phone: normalize before validation to reduce false negatives.
- File uploads: enforce MIME and size checks client-side and server-side.
- Rich text inputs: sanitize on server and encode on render.
- Numeric money fields: use decimal-safe parsing and range checks.
Suggested checks
rg -n "onSubmit|handleSubmit|Form|formik|react-hook-form|yup|zod" frontend/src
rg -n "localStorage|sessionStorage|console\.log\(|Sentry|analytics" frontend/src
rg -n "type=\"file\"|upload|multipart|FormData" frontend/src
Test minimum
- Reject malformed input with stable messaging.
- Ignore rapid double click while request is in flight.
- Preserve user input when recoverable errors occur.
- Avoid stale success state after failed retries.
- Confirm no sensitive values appear in logs or telemetry payloads.
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 First seen · 51 lines · 50 tokens per session scan A 8653ef26b21d
ui-safe-form-patterns is a skill published in the GitHub repository LazyAGI/LazyMind (357 stars, last pushed yesterday), licensed Apache-2.0. It adds 50 tokens to every session and 505 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.
Other skills, from other repositories
unified-llm-api
Call model APIs through @prismshadow/mmsp (MMSP) — streaming text generation, image generation, speech synthesis, embeddings and the supported-model registry with one client.
remote-compute-modal
Run GPU jobs on the user's own Modal account via host.compute.create('byoc:modal', ...). Covers the create→submit→waitfornotification flow, the computeprovider kernel for env setup, image/volume resolution, and the two approval cards. Load once you've decided to dispatch to Modal.
customize
Create, configure, and maintain custom agent profiles and author new skills via the repl tool. Use when the user wants to create an agent profile, build a custom agent, modify agent capabilities, attach or detach skills/connectors on a profile, author a skill, or inspect which connectors and tools are available. Also…
smart-data-analysis
A central workflow for handling data questions and data assets across tables, views, metrics, SQL, charts, and Business Knowledge Networks.
claude-api
Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports anthropic/@anthropic-ai/sdk/claudeagentsdk, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports openai/other AI SDK, general programming, or ML/data-science tasks.
compute-env-setup
Set up a compute environment on a remote provider so Claude Science jobs can run there. Covers direct SSH/conda hosts, Slurm clusters, container-via-bridge runners, and managed-API providers (Modal, GCP, RunPod). Use when standing up a new provider, porting an env to a different backend, adding a tool that needs its…