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 thierryc/Glyphs-mcp --skill glyphs-mcp-litsquare-metadatagit clone --depth 1 https://github.com/thierryc/Glyphs-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/thierryc/glyphs-mcp/glyphs-mcp-litsquare-metadata)<a href="https://agentmods.dev/skills/thierryc/glyphs-mcp/glyphs-mcp-litsquare-metadata"><img src="https://agentmods.dev/badge/skills/thierryc/glyphs-mcp/glyphs-mcp-litsquare-metadata/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/thierryc/glyphs-mcp/glyphs-mcp-litsquare-metadata"><img src="https://agentmods.dev/badge/skills/thierryc/glyphs-mcp/glyphs-mcp-litsquare-metadata.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00069 | $0.01289 |
| Opus 5 | $0.00034 | $0.00645 |
| Sonnet 5 | $0.00014 | $0.00258 |
| Haiku 4.5 | $0.00007 | $0.00129 |
Grade A, and why
glyphs-mcp-litsquare-metadata 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 12d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LitSquare Metadata for Glyphs MCP
Use the typed LitSquare tools. Treat Glyphs' native dictionaries and path attributes as authoritative; JSON is only their transport projection.
The Glyphs MCP Metadata Inspector uses Glyphs' native Palette disclosure control; the plug-in does not force or persist its open/closed state. Every tab uses the same compact JSON text area. Font, Glyph, and Layer edit only the direct com.litsquare value; Paths projects com.litsquare.role as {\"role\": \"body\"} and shows blank text when unassigned. A changed valid value commits once when the text area loses focus. Invalid JSON remains visible and causes no mutation; Escape restores the native baseline. The text.magnifyingglass footer control toggles the active tab into a read-only JSON projection of complete Font/Glyph/Layer userData or every selected path's complete attributes; multiple targets are listed separately with compact identifiers. Diagnostic markers represent native values JSON cannot express directly. The remaining footer controls provide Help, Copy, and Refresh. Palette edits are document-bound, undoable, and never save a font.
Read references/metadata-contract.md before any mutation or role recommendation. The canonical repository copy is metadata-contract.md.
Workflow
- Resolve the exact
font_index, glyph name, layer ID, and selected paths. Stop on ambiguous glyph or layer selection. - Call
get_litsquare_metadatawith inheritance enabled. Read the direct Font, Glyph, and Layer scopes plus effective settings and provenance. - When paths matter, call
get_selected_litsquare_path_roles. Retain every returned glyph name, layer ID, path index, fingerprint, and expected role. - Validate schema support and property-list compatibility. Do not mutate invalid data or a future schema.
- Propose the smallest change. Preserve unknown LitSquare fields, unrelated
userDatanamespaces, and every unrelated path attribute. - Call
patch_litsquare_metadataorset_litsquare_path_rolesin dry-run mode. Present every replacement explicitly. - Confirm only after the user approves the dry-run. Never infer a low-confidence role and never copy inherited values into a narrower scope merely to make them explicit.
- Read the affected metadata or roles again. Report verified results and
fontSaved: false; never save automatically.
What ships with it
2 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.
- 12d ago First seen · 70 lines · 69 tokens per session scan A f94110a2de7f
glyphs-mcp-litsquare-metadata is a skill published in the GitHub repository thierryc/Glyphs-mcp (44 stars, last pushed yesterday), licensed Apache-2.0. It adds 69 tokens to every session and 1,289 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
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 $ultragoal 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.