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 ant-dev-lab/nightmarquee-mcp --skill nightmarquee-wrengit clone --depth 1 https://github.com/ant-dev-lab/nightmarquee-mcpWrote 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/ant-dev-lab/nightmarquee-mcp/nightmarquee-wren)<a href="https://agentmods.dev/skills/ant-dev-lab/nightmarquee-mcp/nightmarquee-wren"><img src="https://agentmods.dev/badge/skills/ant-dev-lab/nightmarquee-mcp/nightmarquee-wren/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/ant-dev-lab/nightmarquee-mcp/nightmarquee-wren"><img src="https://agentmods.dev/badge/skills/ant-dev-lab/nightmarquee-mcp/nightmarquee-wren.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 | $0.00128 | $0.00475 |
| Opus 5.5 | $0.00051 | $0.00190 |
| Sonnet 5.5 | $0.00026 | $0.00095 |
| Haiku 4.5 | $0.00013 | $0.00047 |
Grade A, and why
nightmarquee-wren scanned grade A with 1 finding 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 16d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Without it: `curl -s "https://nightmarquee.com/api/mcp/prompt/wren?tool=claude"` and use the `text` field. What it actually says
Wren
The companion app for a robot that lives with you. Live demo: https://nightmarquee.com/demo/wren
A home-robot app that feels like hardware: a live camera card that tags what the robot sees, a voice orb that turns a sentence into a queued task, a CSS-3D floor plan you spin with a finger while the robot re-plans around a toy, and teach-by-demonstration with a projected 3D skeleton. Ships inside a scroll tour where the phone swings between chapters over the footage.
Get the prompt
The prompt is kept current on nightmarquee.com, so fetch it rather than writing the page from this summary.
- With the NightMarquee MCP server:
nightmarquee_get_prompt(slug: "wren", tool: "claude"). Pass thetoolfor the editor you are in (lovable, bolt, cursor, claude or codex) andbrandfor the person's own name. - Without it:
curl -s "https://nightmarquee.com/api/mcp/prompt/wren?tool=claude"and use thetextfield.
Footage
The demo's clips come with the prompt for anyone signed in to a free NightMarquee account, through the MCP server (nightmarquee_sign_in, then nightmarquee_get_footage(slug: "wren")). Download each clip into public/ under its name before building. Without them, follow the prompt's own footage steps.
Build the page, then compare it with the demo. Prompt licence: https://nightmarquee.com/license
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.
- 16d ago First seen · 24 lines · 128 tokens per session scan A 5f4628dbdf26
nightmarquee-wren is a skill published in the GitHub repository ant-dev-lab/nightmarquee-mcp (1 stars, last pushed 17d ago), licensed MIT. It adds 128 tokens to every session and 475 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-11.
Other skills, from other repositories
accessibility
Use when working on accessibility, a11y, WCAG, ARIA, screen readers, keyboard nav, focus order, contrast, alt text, captions, reduced motion, or target sizes; not language/culture/device (see inclusive-design).
inclusive-design
Use when working on inclusion, i18n/localization, global name/address forms, low-end devices, slow/metered networks, affordability, or first-time/low-confidence users; not WCAG/screen readers (see accessibility).
excalidraw-architect
Choose and compose the right Excalidraw diagram - architecture, flowchart, sequence, state, ER, swimlane, process, timeline, quadrant, pyramid, venn, loop, gantt, bar, line, scatter, and more - using the excalidraw-architect-mcp server. Use whenever a reader would learn more from a picture than from prose, or when…
metago-thought-14-ambient-intelligence
A framework for assessing intelligence built into physical environments, such as smart spaces and embedded systems. It focuses on whether sensing and computing blend naturally into the surroundings and adapt to users.
metago-thought-16-spatial-agent
A framework for designing and evaluating interfaces that use physical space as part of the interaction, such as sensors, projection, augmented reality, voice, or gestures. It treats the environment itself as an interface rather than limiting interaction to a screen.
pn-render-verify
Re-read a rendered or visual artifact and produce a structured verdict against the spec. Use before pn-skeptic-challenge in design workflows when the deliverable is a render, image, screenshot, or HTML page.