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 CloudChef/atlasclaw-providers --skill form-designergit clone --depth 1 https://github.com/CloudChef/atlasclaw-providersWrote 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/cloudchef/atlasclaw-providers/form-designer)<a href="https://agentmods.dev/skills/cloudchef/atlasclaw-providers/form-designer"><img src="https://agentmods.dev/badge/skills/cloudchef/atlasclaw-providers/form-designer/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/cloudchef/atlasclaw-providers/form-designer"><img src="https://agentmods.dev/badge/skills/cloudchef/atlasclaw-providers/form-designer.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 | $0.00046 | $0.04520 |
| Opus 5 | $0.00023 | $0.02260 |
| Sonnet 5 | $0.00009 | $0.00904 |
| Haiku 4.5 | $0.00005 | $0.00452 |
Grade A, and why
form-designer 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 9d 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 — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
form-designer
Design, read, and normalize SmartCMP Angular form schema JSON only. It does not submit requests or save changes.
Current Page Interaction
When this Skill is selected by a SmartCMP form editor Context:
- Call
smartcmp_read_current_form_schemabefore proposing any change. Do not ask the user for the page URL or form ID. - Treat the returned saved schema as the source of truth. Apply only the user's requested changes and preserve unrelated fields, field order, JavaScript strings, unknown keys, visibility rules, and model dependencies.
- Pass the complete updated schema through
smartcmp_design_form_schemawithmode=modifybefore answering. - Return the complete normalized replacement schema. Never use ellipses, snippets, diffs, or summaries in place of unchanged schema content.
- State that the output is for manual review and copying back to CMP. Do not claim that the form was saved, updated, or published.
Boundaries
- No submit/approve/status workflows.
- No CMP form writes: no POST, PUT, PATCH, DELETE, publish, save, or delete.
- Form URLs are read-only source material.
- In an embedded form editor, any explicit
form_urlmust identify the same form as the server-owned page Context. The URL tools reject a different form before issuing a Provider request. Ordinary non-embedded Chat URL workflows remain supported through the selected Provider instance.
Workflow
- New form: if the user gave enough fields, do not read CMP or call datasource tools. Build complete
schema_json, then callsmartcmp_design_form_schemawithmode=new. - Bare form edit/design URL: inspect only. Call
smartcmp_read_form_schema; do not design. - URL plus full field-set or schema-shape changes: treat this as new-form generation with one extra read step. First call
smartcmp_read_form_schemato understand the current form, then generate a fresh complete replacement schema from the user's latest requirements and call design withmode=regenerate. Use the old schema only as context; do not patch, splice, or preserve existing fields/JavaScript unless the user explicitly asks to keep them. - URL plus deterministic projection/composition changes: after the read step, call
smartcmp_design_form_schemawithmode=modify,form_url, andvalue_expressions_json. This lets the tool load the source schema and replace the target expression with the hardened runtime expression instead of asking the LLM to hand-copy the old schema or JavaScript. mode=modifyis only for complete caller-provided JSON, deterministiccatalog_fields_jsoninsertion, or deterministicvalue_expressions_jsonupdates into a suppliedschema_jsonorform_urlsource. Never callmode=modifywith onlymodeor only insertion/update JSON; that would create an incomplete replacement schema.- If a read result warns that a field expression is not
function(model, sourceParams, schema, unused, cfg), do not answer by hand-writing a replacementschema_jsonwith another legacy signature such asfunction(formInRet, schemas, widget, injection). For catalog/model value rewrites, usevalue_expressions_json; for custom JavaScript, provide a complete modern-signature expression that writesmodel[fieldKey]. - If read/design output reports
designMode,modelKeys, orcomponentCount, tell the user the source form has visual-designer/model state that can preserve stale runtime values even when the schema expression changes. The generated schema is still a manual replacement draft; SmartCMP persistence and visual designer state must be reviewed in CMP.
What ships with it
2 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.
- 9d ago First seen · 223 lines · 46 tokens per session scan A 3b85ee591e54
form-designer is a skill published in the GitHub repository CloudChef/atlasclaw-providers (15 stars, last pushed 5d ago), licensed Apache-2.0. It adds 46 tokens to every session and 4,520 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI).…
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
tutti-ui-system
Use when working with @tutti-os/ui-system components, replacing local UI with shared components, querying component ids or metadata, promoting UI into shared base or business components, or maintaining UI-system storyboard inventory.
design-review
Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues in source code, committing each fix atomically and re-verifying with before/after screenshots. For plan-mode design review (before implementation), use…
mcp-host-styling-integration
Integrates MCP App UI with host theming system. Applies host CSS variables, handles onhostcontextchanged, safe area insets, display mode detection, and fullscreen configuration.
moai-design-tools
Design tool integration specialist covering Figma MCP, Pencil renderer, and Pencil-to-code export. Use when fetching design context from Figma, rendering Pencil designs, or exporting to React/Tailwind code.