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 regen-coordination/org-os-template --skill paper-designgit clone --depth 1 https://github.com/regen-coordination/org-os-templateWrote 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/regen-coordination/org-os-template/paper-design)<a href="https://agentmods.dev/skills/regen-coordination/org-os-template/paper-design"><img src="https://agentmods.dev/badge/skills/regen-coordination/org-os-template/paper-design/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/regen-coordination/org-os-template/paper-design"><img src="https://agentmods.dev/badge/skills/regen-coordination/org-os-template/paper-design.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 | $0.00068 | $0.02373 |
| Opus 5.5 | $0.00027 | $0.00949 |
| Sonnet 5.5 | $0.00014 | $0.00475 |
| Haiku 4.5 | $0.00007 | $0.00237 |
Grade A, and why
paper-design 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 29d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Design
Paper (https://paper.design) is a canvas whose every element is real HTML/CSS. Its MCP server runs
locally from Paper Desktop (http://127.0.0.1:29979/mcp) and exposes read tools, write tools, tokens,
export and comment threads. This skill is the method; the drawing happens through Paper's own tools.
packages/paper-integration/ only guarantees health, token sync and token drift — read
docs/integrations/paper.md for the runbook and the module's current status.
When to Use
- Asked to draft, refine, or export a visual artifact on a Paper canvas — a social card, poster, deck slide, page mock, or any composition already described in the org's DESIGN.md.
- Brand tokens are already pushed to the target Paper file (
npm run paper:lint-tokenspasses), or can be pushed first withpaper:push-tokens. - A human has left comments on an existing artboard that need addressing — see The review loop, below.
When NOT to Use
- For an org whose tokens are not the ones currently pushed to the target Paper file — never use another org's artifact as the style reference.
- To pick a colour, size, or weight that has no token. Derive it into the org's own stylesheet and push the token first; this skill draws from tokens, it does not invent brand values.
- Past the 25-call per-artifact budget. Export what exists and stop — see Budget, below.
Budget — read first
The free tier allows 100 metered MCP tool calls per week. initialize/tools/list are free; every
tools/call is metered — including one that Paper rejects, since a response still came back. Per
artifact: 25 calls, hard stop. At 25, export what exists, release working indicators, report — do not
"finish quickly". Typical spend for one composition:
| step | calls |
|---|---|
get_basic_info · get_font_family_info([brand face]) · create_artboard |
3 |
write_html, one visual group each |
6–10 |
get_screenshot (max 3) · targeted update_styles / set_text_content (max 3) |
≤6 |
find_nodes colour audit · export · get_jsx · finish_working_on_nodes |
4 |
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.
- 29d ago First seen · 153 lines · 68 tokens per session scan A 85f4640b0b8a
paper-design is a skill published in the GitHub repository regen-coordination/org-os-template (5 stars, last pushed 2d ago), licensed MIT. It adds 68 tokens to every session and 2,373 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 2026-09-19.
Other skills, from other repositories
cloud-design-patterns
Choose and compare cloud design patterns for distributed systems. Use when reviewing architecture, selecting workload patterns, or mapping reliability, performance, messaging, security, and migration concerns to concrete design options.
design-kpi-dashboard
Use when building or redesigning a performance dashboard to track organizational, team, or product KPIs and support data-driven decisions.
json-canvas
Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections. Use when working with .canvas files, creating visual canvases, mind maps, flowcharts, or when the user mentions Canvas files in Obsidian.
playground
Creates interactive HTML playgrounds — self-contained single-file explorers that let users configure something visually through controls, see a live preview, and copy out a prompt. Use when the user asks to make a playground, explorer, or interactive tool for a topic.
ui-skills
Opinionated constraints for building better interfaces with agents.
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.