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 formio/ai --skill formio-angular-formgit clone --depth 1 https://github.com/formio/aiWrote 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/formio/ai/formio-angular-form)<a href="https://agentmods.dev/skills/formio/ai/formio-angular-form"><img src="https://agentmods.dev/badge/skills/formio/ai/formio-angular-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/formio/ai/formio-angular-form"><img src="https://agentmods.dev/badge/skills/formio/ai/formio-angular-form.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 | $0.00221 | $0.05771 |
| Opus 5.5 | $0.00088 | $0.02308 |
| Sonnet 5.5 | $0.00044 | $0.01154 |
| Haiku 4.5 | $0.00022 | $0.00577 |
Grade A, and why
formio-angular-form scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Embedding a Form.io form in Angular
Nested sub-skill.
formio-angular-form/SKILL.mdsits inside theformio-angularskill folder, besideformio-angular-resources. Thename: formio-angular-formfrontmatter is there so recursive-scan clients classify the file; it is not a separately-registered top-level skill. Theformio-angularparent reaches this document the same way it reachesSETUP.mdandAUTH.md— it is loaded by path. Never invoke it by frontmatter name; open the file.
One component
FormioComponent from @formio/angular, as the element <formio>:
<formio [src]="formUrl" (submit)="onSubmit($event)"></formio>
That is the whole entry point. It fetches the definition, renders it, saves the submission, places server errors on the fields that caused them, and shows its own alert and loading chrome. Its inputs are reactive, so a parent can change the form, the submission, or the language after the first render.
There is no component decision to make on arrival. When <formio> is genuinely the wrong tool — a form mounted outside Angular's tree, a page that must not carry @formio/angular at all — the second path is the renderer itself, and references/renderer-directly.md is where that goes. It is a different job, not a different component.
Capture the workspace root first
This branch is exempted from the parent skill's workspace pre-flight, so nothing has captured a path for it — and everything below runs commands and edits files. Capture one absolute path before the first of them: the directory the user invoked you from, which is the working directory this session started in, NOT the output of a pwd run after other commands. A shell working directory persists between commands in an agent session, so one cd earlier in the turn retargets every relative path after it.
Call it workspaceRoot, give every command its own directory (cd "<workspaceRoot>" && <command>), read and write files at absolute paths under it, and pass it as cwd to project_get when references/config.md needs the project URLs. If you cannot account for where the shell currently is, state the path you intend to use and confirm it before touching anything.
What ships with it
8 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.
- 3d ago Changed 6565f4226565
- 4d ago Changed · +12 tokens per session 3b7b62e5edf2
- 7d ago Changed ccedbe9472a9
- 18d ago Changed · +3 lines 571eceefd278
- 1mo ago Changed · +1 lines 7b8ba8448948
- 1mo ago First seen · 188 lines · 209 tokens per session scan A 9eeafa0c56b2
formio-angular-form is a skill published in the GitHub repository formio/ai (8 stars, last pushed 2d ago), licensed MIT. It adds 221 tokens to every session and 5,771 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 2026-09-09.
Other skills, from other repositories
ideogram-ultra
Build Ideogram 4 (Ideogram Ultra) txt2img and img2img workflows with the local open-weights model, dual conditional/unconditional models with DualModelGuider, Qwen3-VL text encoder, and structured JSON ("compositional deconstruction") prompts for strong text rendering and layout control.
model-compatibility
Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models.
flux-txt2img
Build Flux txt2img workflows with Flux.1 Dev (SRPO), Flux 2 Klein 9B, Turbo LoRAs, FluxGuidance, and DualCLIPLoader patterns.
civitai
Discover Civitai models with the BUILT-IN downloadmodel action:"searchcivitai" and install/generate them locally. Find a checkpoint/LoRA/embedding on Civitai, download it into ComfyUI, and use its trigger words. Optionally pair the official Civitai MCP for community features (images browsing, posting, collections).
dev
One-command dev loop boot. Spins up portless (named HTTPS subdomain), emulate (stateful API mocks), the project's dev server, and an agent-browser session, all keyed to the current git branch. Use when starting a feature branch, switching worktrees, or returning to a project after a break. Skips silently with install…
storybook-mcp-integration
Reference for the Storybook MCP server itself (@storybook/addon-mcp): 6 tools across 3 toolsets (dev, docs, testing), availability detection, and per-agent toolset filtering. Use when setting up the server or calling these tools directly against components that already exist. For the end-to-end pipeline that turns a…