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 open-circle/agent-skills --skill formischgit clone --depth 1 https://github.com/open-circle/agent-skillsWrote 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/open-circle/agent-skills/formisch)<a href="https://agentmods.dev/skills/open-circle/agent-skills/formisch"><img src="https://agentmods.dev/badge/skills/open-circle/agent-skills/formisch/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/open-circle/agent-skills/formisch"><img src="https://agentmods.dev/badge/skills/open-circle/agent-skills/formisch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
- Socket pass
- Snyk 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 | $0.00068 | $0.08322 |
| Opus 5.5 | $0.00027 | $0.03329 |
| Sonnet 5.5 | $0.00014 | $0.01664 |
| Haiku 4.5 | $0.00007 | $0.00832 |
Grade A, and why
formisch 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 8d 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 — 1,166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Formisch
This skill helps AI agents work effectively with Formisch, the schema-based, headless form library for modern frameworks.
When to Use This Skill
- When the user asks about form handling with Formisch
- When managing form state and validation
- When working with Angular, HonoX, Preact, Qwik, React, React Native, Solid, Svelte, or Vue forms
- When integrating Valibot schemas with forms
Introduction
Formisch is a schema-based, headless form library that works across multiple frameworks. Key highlights:
- Small bundle size — Starting at ~2.5 kB
- Schema-based validation — Uses Valibot for type-safe validation
- Headless design — You control the UI completely
- Type safety — Full TypeScript support with autocompletion
- Framework-native — Native performance for each supported framework
Supported Frameworks
| Framework | Package | Hook/Primitive |
|---|---|---|
| Angular | @formisch/angular |
injectForm |
| HonoX | @formisch/honox |
useForm |
| Preact | @formisch/preact |
useForm |
| Qwik | @formisch/qwik |
useForm$ |
| React | @formisch/react |
useForm |
| React Native | @formisch/react-native |
useForm |
| SolidJS | @formisch/solid |
createForm |
| Svelte | @formisch/svelte |
createForm |
| Vue | @formisch/vue |
useForm |
Experimental SolidJS 2 support is available through the @formisch/solid/v2 entry point of @formisch/solid (v1.2.0 or later). It requires solid-js and @solidjs/web v2. The default @formisch/solid entry point targets SolidJS 1.
Installation
1. Install Valibot (peer dependency)
npm install valibot
2. Install Formisch for your framework
npm install @formisch/react # React
npm install @formisch/angular # Angular
npm install @formisch/vue # Vue
npm install @formisch/solid # SolidJS
npm install @formisch/preact # Preact
npm install @formisch/svelte # Svelte
npm install @formisch/qwik # Qwik
npm install @formisch/react-native # React Native
npm install @formisch/honox # HonoX
What ships with it
1 file 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.
- 8d ago Changed · +2 lines b36b225c3357
- 9d ago Changed · +45 lines · +4 tokens per session 1f6585845a8f
- 2mo ago First seen · 1,119 lines · 64 tokens per session scan A 20d7ec7777e3
formisch is a skill published in the GitHub repository open-circle/agent-skills (17 stars, last pushed 9d ago), licensed MIT. It adds 68 tokens to every session and 8,322 once invoked, about $0.0003 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.
formisch compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| formischopen-circle/agent-skills | Skill | 17 | 9d ago | MIT | A | 68 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |