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 agentmods add commands/adilkalam/orca/typographygit clone --depth 1 https://github.com/adilkalam/orcaWhat 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 | $0.00015 | $0.03123 |
| Opus 5 | $0.00008 | $0.01562 |
| Sonnet 5 | $0.00003 | $0.00625 |
| Haiku 4.5 | $0.00002 | $0.00312 |
Grade A, and why
typography 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 yesterday.
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.
/typography Reduce the curl on terminals in DomaineSansCustom (a, c, e, f, g, j, r, s, t, y) How it starts
The opening of the file, as written. The whole thing — 411 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/typography - Font Library Management Pipeline
REQUEST: $ARGUMENTS
Overview
The /typography command (main thread) runs the typography workflow directly, spawning specialists single-level via Agent(). There is no intermediate orchestrator subagent — the command owns routing, checkpoints, and Workshop persistence. It handles:
- Glyph editing - Surgical contour modifications with fontTools
- TTF export - OTF to TTF conversion for Epson LabelWorks
- Font selection - Recommendations and pairing suggestions
- Typography Explorer - Generate interactive testing tools for real-time typography exploration
Mandatory Pre-Flight
Before ANY operation:
- Read CLAUDE.md - Source of truth for paths and rules
- Check sacred collections - NEVER modify [Adobe], [FontShop], Google Fonts, Nerd Fonts, Icons
- Verify paths - Use canonical paths from CLAUDE.md
Complexity Routing
Parse $ARGUMENTS for complexity tier:
| Flag | Tier | Routing |
|---|---|---|
--tweak |
Simple | Direct to specialist, no checkpoints |
| (none) | Default | Full workflow with backup + batch checkpoints |
--complex |
Complex | Full pipeline with per-weight previews |
--explorer |
Tool Generation | Generate typography exploration tool |
Explorer Mode (--explorer)
When $ARGUMENTS contains --explorer, the command spawns the typography-explorer-generator agent single-level.
Usage
/typography --explorer # Generate typography tester (auto-detect format)
/typography --explorer --nextjs # Generate as Next.js app
/typography --explorer --html # Generate as standalone HTML
/typography --explorer --context store # For store/product UI context
/typography --explorer --context markdown # For article/markdown context
Format Detection
- If
--nextjsflag present: Generate Next.js React components - If
--htmlflag present: Generate standalone HTML file - Otherwise, auto-detect:
- Check for
next.config.*in project root - If found: Next.js format
- Otherwise: HTML format
- Check for
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.
- yesterday First seen · 411 lines · 15 tokens per session scan A cc4e02ad9a83
typography is a command published in the GitHub repository adilkalam/orca (2 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 3,123 once invoked, about $0.0001 per session on Opus 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 2026-08-31.
Other commands, from other repositories
e2e
使用 Playwright 对 Web UI 进行端到端测试（支持视频录制、Trace 录制、控制台/网络日志捕获）.
auto-browse
Auto-browse — learn, optimize, and graduate browser operations or web data-mining workflows.
research-perplexity
Run a deep research query using Perplexity's /research mode via Playwright browser automation. This is an alternative to /export-to-council that uses Perplexity's dedicated research mode instead of multi-model council.
review
Compare a reference design against an implementation. Accepts Figma URL, image file, or browser URL as reference.
graphify
Turn your vault into a clustered knowledge graph with HTML and JSON outputs.
laravel-playwright
E2E Playwright patterns; use the laravel:e2e-playwright skill exactly as written.