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 BlackBeltTechnology/pi-agent-dashboard --skill openforms-muigit clone --depth 1 https://github.com/BlackBeltTechnology/pi-agent-dashboardWrote 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/blackbelttechnology/pi-agent-dashboard/openforms-mui)<a href="https://agentmods.dev/skills/blackbelttechnology/pi-agent-dashboard/openforms-mui"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/openforms-mui.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 MCP Rug Pull · line 132 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 | $0.00131 | $0.02216 |
| Opus 5 | $0.00066 | $0.01108 |
| Sonnet 5 | $0.00026 | $0.00443 |
| Haiku 4.5 | $0.00013 | $0.00222 |
Grade A, and why
openforms-mui 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 5d 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
openforms-mui
Runtime interpreter that renders an OpenForms FormSchemaJSON as MUI. Walk the
schema on every render — no code generation, no emitted per-form files. The
component mirrors the upstream OpenFormRenderer API so migration is a
mechanical substitution.
What this skill is (and is not)
- Is: a React + MUI runtime for the visual form-builder schema from
github.com/henriquefps/open-forms(Apache 2.0). It implements all 14 field types, both conditional-logic systems, calculated fields, and validation. - Is not: the
open-form.dev"documents as code" framework. If a request is aboutopen-form.dev, this skill does not apply.
Where it lives
~/.pi/agent/skills/openforms-mui/
SKILL.md
references/ # load only the one you need
schema.md # FormSchemaJSON structure
field-widget-map.md # 14 types → MUI widget → value shape
logic.md # CNF andGroups, operators, formula grammar
theme-bridge.md # tokens → createTheme(); host theme provider
a11y.md # matrix / repeater / signature pitfalls
hu-locale.md # Hungarian conventions (opt-in via locale)
tools/ # the TypeScript library + preview harness
src/ # component, schema, logic, validation, theme, i18n
preview/ # Vite three-panel harness + CLI
tests/ # vitest suite
mockups/ # approved token layer (tokens.css, ui-contract.tokens.json)
The skill is user-global — usable from any working directory, with no assumption about any particular project or document archive.
Using the component in a project
import { OpenFormsMui } from "openforms-mui"; // resolves to tools/src/index.ts
<OpenFormsMui
schema={schema}
answers={initialAnswers}
readOnly={false}
locale="en" // "hu" enables the Hungarian UI dictionary
onSubmit={(answers, meta) => {
// answers: upstream-shaped, keyed by field key (applicable fields only)
// meta.submissionContext: your supplementary data, segregated from answers
// meta.diagnostics: non-blocking findings (e.g. disabled/calculated violations)
}}
onFieldChange={(all) => {/* COMPLETE state incl. retained hidden values — not the payload */}}
/>
What ships with it
60 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.
- references/a11y.md 3.5 KB
- references/field-widget-map.md 3.5 KB
- references/hu-locale.md 1.7 KB
- references/logic.md 4.3 KB
- references/schema.md 4.1 KB
- references/theme-bridge.md 2.2 KB
- tools/.npmignore 36 B
- tools/canvas-serve.mjs 1.8 KB runs code
- tools/demo-schema.json 3.2 KB
- tools/mockups/tokens.css 813 B
- tools/mockups/ui-contract.tokens.json 703 B
- tools/package-lock.json 191 KB
- tools/package.json 1.7 KB
- tools/preview/canvas-app.tsx 2.1 KB
- tools/preview/canvas-index.html 446 B
- tools/preview/cli.ts 3.6 KB runs code
- tools/preview/index.html 442 B
- tools/preview/main.tsx 8.5 KB
- tools/preview/RenderPanel.tsx 3.5 KB
- tools/preview/vite-plugin.ts 1.5 KB runs code
- tools/scripts/assert-peer-deps.mjs 1.3 KB runs code
- tools/src/css.d.ts 92 B runs code
- tools/src/fields/context.tsx 1.2 KB
- tools/src/fields/ErrorSummary.tsx 2.3 KB
- tools/src/fields/FieldRenderer.tsx 12 KB
- tools/src/fields/FieldShell.tsx 1.6 KB
- tools/src/fields/FileField.tsx 3.2 KB
- tools/src/fields/index.ts 421 B runs code
- tools/src/fields/label.ts 1.7 KB runs code
- tools/src/fields/MatrixField.tsx 5.7 KB
- tools/src/fields/renderer-registry.ts 1.6 KB runs code
- tools/src/fields/RepeaterField.tsx 3.2 KB
- tools/src/fields/SignatureCanvas.tsx 3.4 KB
- tools/src/fonts.ts 353 B runs code
- tools/src/i18n/dictionary.ts 2.0 KB runs code
- tools/src/i18n/hu.ts 2.3 KB runs code
- tools/src/i18n/index.ts 1.4 KB runs code
- tools/src/index.ts 1.2 KB runs code
- tools/src/logic/cnf.ts 6.9 KB runs code
- tools/src/logic/formula.ts 7.8 KB runs code
- tools/src/logic/index.ts 116 B runs code
- tools/src/logic/operators.ts 1.2 KB runs code
- tools/src/logic/state.ts 6.7 KB runs code
- tools/src/OpenFormsMui.tsx 15 KB
- tools/src/payload.ts 3.2 KB runs code
- tools/src/provenance.ts 1002 B runs code
- tools/src/schema/diagnose.ts 9.1 KB runs code
- tools/src/schema/index.ts 149 B runs code
- tools/src/schema/normalize.ts 5.6 KB runs code
- tools/src/schema/types.ts 8.1 KB runs code
- tools/src/schema/walk.ts 2.4 KB runs code
- tools/src/theme/from-tokens.ts 3.8 KB runs code
- tools/src/theme/index.ts 34 B runs code
- tools/src/validation/constrain.ts 2.7 KB runs code
- tools/src/validation/diagnostics.ts 2.4 KB runs code
- tools/src/validation/empty.ts 1.6 KB runs code
- tools/src/validation/index.ts 163 B runs code
- tools/src/validation/resolver.ts 660 B runs code
- tools/src/validation/zod-from-schema.ts 6.4 KB runs code
- tools/tests/a11y.test.tsx 3.6 KB
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.
- 5d ago First seen · 188 lines · 131 tokens per session scan A 558011c4a801
openforms-mui is a skill published in the GitHub repository BlackBeltTechnology/pi-agent-dashboard (276 stars, last pushed yesterday), licensed MIT. It adds 131 tokens to every session and 2,216 once invoked, about $0.0007 per session on Opus 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 2026-09-03.
Other skills, from other repositories
rn-best-practices
This skill should be used when writing or reviewing React Native / Expo code — before writing list rendering, animations, data fetching, component APIs, navigation, or image/media UI — and when asked to "review best practices", "check performance", "optimize renders", "review list rendering", "check animation…
rn-feature-dev
Explicit Codex workflow: Guided feature development for React Native — explore codebase, design architecture, implement, verify live on device, and review quality.
vercel-composition-patterns
React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.
vercel-react-best-practices
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance…
react
Frontend component library.
agency-frontend-developer
Expert frontend developer specializing in modern web technologies, React/Vue/Angular frameworks, UI implementation, and performance optimization.