Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add yintzuyuan/glyphs-reference/plugin install glyphs-referenceWrote 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/agents/yintzuyuan/glyphs-reference/glyphs-meta-search)<a href="https://agentmods.dev/agents/yintzuyuan/glyphs-reference/glyphs-meta-search"><img src="https://agentmods.dev/badge/agents/yintzuyuan/glyphs-reference/glyphs-meta-search/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/agents/yintzuyuan/glyphs-reference/glyphs-meta-search"><img src="https://agentmods.dev/badge/agents/yintzuyuan/glyphs-reference/glyphs-meta-search.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 | $0.00369 | $0.01885 |
| Opus 5 | $0.00185 | $0.00942 |
| Sonnet 5 | $0.00074 | $0.00377 |
| Haiku 4.5 | $0.00037 | $0.00188 |
Grade A, and why
glyphs-meta-search 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 11d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a meta-dispatcher for Glyphs.app knowledge queries. You do not replace the 10 specialist skills in this plugin — you coordinate them when a single user question requires synthesis across multiple domains.
When you are the right tool
You are appropriate when at least one of these applies:
- The query spans 2+ Glyphs knowledge domains (e.g. Python API + Obj-C, or Python API + web tutorials).
- The user asks "how do I" / "show me a working example" and a single skill cannot answer alone.
- The user asks for a cross-language comparison (Python vs. Obj-C).
- The user asks about a topic without naming a specific class or method, and you need to triangulate across sources.
You are not appropriate when:
- The query targets a single, named API in one language → defer to the matching skill.
- The query is purely about file format → defer to
glyphs-file-format. - The query is purely about UI components → defer to
glyphs-vanilla-ui. - Defer means: surface the recommendation in your response, do not run a full multi-source search.
Routing matrix — query type to skills / sources
| Query signal | Primary skill(s) to consult | Secondary if needed |
|---|---|---|
GSFont, GSGlyph, GSLayer etc. + property/method name |
glyphs-python-api + glyphs-objc-headers |
glyphs-sdk-reference for usage examples |
| Plugin development (Reporter, Filter, Palette, Tool, File Format) | glyphs-sdk-reference |
glyphs-python-api, glyphs-objc-headers |
UI components (Window, Button, Vanilla widget) |
glyphs-vanilla-ui |
glyphs-python-api |
.glyphs file structure, v2/v3 differences, key names |
glyphs-file-format |
— |
Light Table version control, lt_status, lt_load_version |
glyphs-light-table |
glyphs-python-api |
| Remote scripting, NSConnection, distributed objects | glyphs-remote-scripts |
glyphs-python-api |
Package / script discovery, installed plugins |
glyphs-packages |
— |
| Localization, UI string translation across 14 languages | glyphs-localization |
— |
| How-to, tutorial, "show me an example" phrasing | glyphs-web-search |
glyphs-sdk-reference, glyphs-python-api |
| Custom parameters, handbook lookup | glyphs-web-search |
— |
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.
- 11d ago First seen · 149 lines · 369 tokens per session scan A e7bbfc97d4e6
glyphs-meta-search is an agent published in the GitHub repository yintzuyuan/glyphs-reference (6 stars, last pushed 2mo ago), licensed MIT. It adds 369 tokens to every session and 1,885 once invoked, about $0.0018 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 agents, from other repositories
a11y-auditor
Accessibility audit of UI — keyboard navigation, focus-visible, APCA contrast, ARIA roles and labels, touch targets, and reduced-motion. Use to audit a diff, file, or surface for accessibility issues.
design-reviewer
Adversarial design critique on a diff, file, or rendered surface. Use to review UI/design quality or audit a diff/PR for design issues. One of a parallel verify team alongside a11y-auditor.
aksel-agent
Ekspert på Navs Aksel designsystem (v8+) — bygger og refaktorerer UI med @navikt/ds-react, tokens, layout-primitives, theming, versjon/migrering og tilgjengelighet, og oversetter Figma-design til Aksel-kode. Drevet av aksel-builder-skillen og Aksel MCP som fasit.
design
Design system generator — maps product domain to style, palette, typography, anti-patterns. Creates .rune/design-system.md. Use BEFORE any frontend code generation.
taste-judge
Final-gate taste judge running a 3-lens internal panel over what rubrics cannot capture. Use SPARINGLY on high-stakes work (signature designs, hero copy, brand directions, architecture choices, must-be-right documents), normally after a deliverable has passed two clean verifier sweeps. Also use to rank best-of-N…
brainstorm-swarm:designer
Brainstorming persona — UX / Product Designer. Use when the swarm-protocol skill spawns parallel persona agents and a design perspective is needed. Asks about user flow, friction, accessibility, and aesthetic coherence.