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 lucidsoftware/lucid-mcp-server --skill lucidgit clone --depth 1 https://github.com/lucidsoftware/lucid-mcp-serverWrote 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/lucidsoftware/lucid-mcp-server/lucid)<a href="https://agentmods.dev/skills/lucidsoftware/lucid-mcp-server/lucid"><img src="https://agentmods.dev/badge/skills/lucidsoftware/lucid-mcp-server/lucid.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 5.1 | $0.00055 | $0.00552 |
| Opus 5 | $0.00028 | $0.00276 |
| Sonnet 5 | $0.00011 | $0.00110 |
| Haiku 4.5 | $0.00006 | $0.00055 |
Grade A, and why
lucid 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 7d 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lucid
Use the currently exposed Lucid MCP tools as the source of truth.
Workflow
- Match the user's goal to the most specific available Lucid MCP tool.
- Prefer stable IDs or URLs. Search/list before asking when discovery is possible.
- Read any required
lucid://...resource before calling a tool that requires it. - Fetch current document/page/item state before editing existing content.
- Ask for one missing source artifact when creation or modification depends on unavailable input.
- Confirm before destructive actions, bulk changes, broad permission changes, or anonymous share links.
- Report the affected document/page/item/thread IDs, returned URLs, exported files, and key assumptions.
Intent Routing
- For discovery, history, folders, or unknown documents, use search/list tools before asking for an ID.
- For large documents, search distinctive text first, then fetch only the relevant page or region when possible.
- For document understanding, fetch the smallest useful scope and summarize only MCP-provided content.
- For edits, fetch or search first to identify current page/item IDs and nearby context.
- For creation, use the most specific creator available. For general diagram/import tools, follow all tool prerequisites and required resources.
- For export, sharing, comments, or collaboration, prefer exact document/thread IDs and report returned files, URLs, roles, or comment IDs.
Source Dependency Gate
- Before creating or modifying Lucid content, check whether the request depends on an unavailable source artifact such as an uploaded file, link, spreadsheet, PDF, image, selected content, prior diagram, or pasted text.
- If required source content is missing, ask one concise question for it. Do not generate a generic substitute.
Guardrails
- Treat MCP responses as ground truth. Do not invent document contents, object IDs, resource names, supported shapes, or tool capabilities.
- Use Lucid resource libraries when tool descriptions reference them.
- Read current document state before editing existing content.
- Re-fetch or otherwise verify after meaningful edits when practical.
- Confirm first when the operation is destructive, broad, permission-related, anonymous-sharing-related, or ambiguous in scope.
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.
- 7d ago First seen · 40 lines · 55 tokens per session scan A a9260cebb9d6
lucid is a skill published in the GitHub repository lucidsoftware/lucid-mcp-server (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 55 tokens to every session and 552 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 2026-08-31.
Other skills, from other repositories
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.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.