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 webflow/webflow-skills --skill interactionsgit clone --depth 1 https://github.com/webflow/webflow-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/webflow/webflow-skills/interactions)<a href="https://agentmods.dev/skills/webflow/webflow-skills/interactions"><img src="https://agentmods.dev/badge/skills/webflow/webflow-skills/interactions/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/webflow/webflow-skills/interactions"><img src="https://agentmods.dev/badge/skills/webflow/webflow-skills/interactions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
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 →
- high Anti-Refusal · line 351 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
- medium Excessive Agency · line 77 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 106 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium MCP Rug Pull · line 706 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 | $0.00063 | $0.10289 |
| Opus 5.5 | $0.00025 | $0.04116 |
| Sonnet 5.5 | $0.00013 | $0.02058 |
| Haiku 4.5 | $0.00006 | $0.01029 |
Grade A, and why
webflow-mcp:interactions 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.
The source is not reproduced here
Licensed MIT
The repository is licensed MIT, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
What ships with it
17 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/actions-and-properties.md 35 KB
- references/capabilities.generated.md 9.2 KB
- references/conditional-playback.md 1.7 KB
- references/envelope-and-targets.md 18 KB
- references/gated-capabilities.md 4.4 KB
- references/index.md 9.5 KB
- references/limits-and-budgets.md 4.2 KB
- references/panel-traps.md 12 KB
- references/rejects-index.md 28 KB
- references/timelines-and-groups.md 8.3 KB
- references/trigger-click.md 4.3 KB
- references/trigger-custom.md 2.7 KB
- references/trigger-hover.md 12 KB
- references/trigger-load.md 2.5 KB
- references/trigger-mouse-move.md 10 KB
- references/trigger-scroll.md 10 KB
- references/updating-interactions.md 9.2 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.
- 1mo ago Changed · -1 lines · -16 tokens per session e93b84d45fe0
- 1mo ago Changed · +6 lines a2e2aa61238a
- 1mo ago Changed · +4 lines c07ec37bd658
- 1mo ago First seen · 714 lines · 79 tokens per session scan A f400ea868b62
webflow-mcp:interactions is a skill published in the GitHub repository webflow/webflow-skills (132 stars, last pushed today), licensed MIT. It adds 63 tokens to every session and 10,289 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 2026-09-03.
Other skills, from other repositories
web-design-engineer
Build or redesign polished browser-rendered visual artifacts with HTML/CSS/JavaScript/React: pages, dashboards, prototypes, slide decks, animations, UI mockups, and data visualizations. Use for visual front-end creation, design-system exploration, design critique, or explicit browser acceptance / QA of a web artifact.…
yida-data-manage-ui
A method for improving the appearance and usability of Yida data-management pages, while keeping their data, permissions, queries, and business actions unchanged. Yida is a platform for building business applications.
frontend-blueprint
AI frontend specialist and design consultant that guides users through a structured discovery process before generating any code. Collects visual references, design tokens, typography, icons, layout preferences, and brand guidelines to ensure the final output matches the user's vision with high fidelity. Use when the…
ardot-style-guide
A design-system workflow for choosing and applying colors, fonts, spacing, and page layouts in Ardot projects.
design-optimizer
Optimize a website or app design in one run: capture the page once, audit usability, UX/AX, virality and agent readiness, merge overlaps into one prioritized report, apply fixes on opt-in. Don't use for one lens (dont-make-me-think, ux-ax-review).
cf-design
UI design workflow — scan patterns, design new UI, or modify UI consistently. Use to redesign a component/page, change colors/typography/style, or extract the design system. Triggers: "make it look like", "update the styling", "redesign this", "match the existing style", "add a dark mode", "make it more minimal".