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 agentmods add skills/fredm00n/framerlabs/framer-pluginsnpx skills add fredm00n/framerlabs --skill framer-pluginsgit clone --depth 1 https://github.com/fredm00n/framerlabsWrote 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/fredm00n/framerlabs/framer-plugins)<a href="https://agentmods.dev/skills/fredm00n/framerlabs/framer-plugins"><img src="https://agentmods.dev/badge/skills/fredm00n/framerlabs/framer-plugins.svg" alt="Measured on agentmods" 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 | $0.00055 | $0.04653 |
| Opus 5 | $0.00028 | $0.02327 |
| Sonnet 5 | $0.00011 | $0.00931 |
| Haiku 4.5 | $0.00006 | $0.00465 |
Grade A, and why
framer-plugins 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 — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Framer Plugin Development Guide
You are an expert on the Framer Plugin SDK. Use this reference when building, debugging, or modifying Framer plugins. Always check the project's CLAUDE.md for project-specific overrides.
Quick Reference
- SDK package:
@framer/plugin(v4+, the Framer 3.0 release). Renamed fromframer-plugin, which is now deprecated on npm — never use the old name. - Scaffolding:
npm create framer-plugin@latest(thecreate-framer-pluginscaffolder keeps its name and installs@framer/plugin) - Build: Vite +
vite-plugin-framer(name unchanged;framer-plugin-toolspackCLI also unchanged) - Base styles:
import "@framer/plugin/framer.css"(optional:import "@framer/plugin/inter.css"to load Inter alone) - Core import:
import { framer } from "@framer/plugin" - Dev workflow:
npm run dev→ Framer → Developer Tools → Development Plugin
SDK v4 (2026-06-16) and the recent v3.x additions
v4.0 itself is mostly the rename (version attributions verified against the official changelog 2026-07-13). Shipped in v4: the package rename framer-plugin → @framer/plugin (current stable 4.0.1; the old package is deprecated on npm; migration is a mechanical find-replace — no commonly-used API was removed; peerDeps react/react-dom ^18.2.0, csstype ^3.1.1), a restyled framer.css (Framer 3.0 design: new Inter character alternates, selection colors, input element styles — re-check custom input/selection styling after upgrading; new @framer/plugin/inter.css export loads Inter alone), WebPageNode.clone() / DesignPageNode.clone(), an optional filter on getLocalizationGroups(), new frame/text link attributes, and setParent accepting UnknownNode.
Added during v3.x (2025 – early 2026) — newer than many published examples, none permission-gated:
framer.navigateTo(nodeId, opts?)(3.7.0) — selects + zooms a node into view (opts: { select?=true, zoom? }). Instance forms:node.navigateTo(),collectionItem.navigateTo(),codeFile.navigateTo(). Ideal right after an insert/replace.framer.setMenu(items)andframer.showContextMenu(items, config)(3.5.2) — global window-header menu + context menus anywhere in the plugin UI.framer.subscribeToOpenCodeFile(cb)(3.7.0) — fires when the user opens/switches code files.- Design Pages (3.8.0): read/create/edit nodes on Design Pages via the same Nodes + Selection APIs.
- CMS: access all Collections (not just plugin-managed) and write to unmanaged collections (Plugins 3.0, Mar 2025);
framer.createManagedCollection()(3.10.2);framer.setCloseWarning()(3.10.3).framer.getManagedCollection()is deprecated → usegetActiveManagedCollection()(the deprecation is in the d.ts; the CMS docs page still shows the old call in examples).
What ships with it
5 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.
- 5d ago First seen · 264 lines · 55 tokens per session scan A 2ec5eee3d54e
framer-plugins is a skill published in the GitHub repository fredm00n/framerlabs (134 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 4,653 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…