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 skills/yonatangross/orchestkit/glyphnpx skills add yonatangross/orchestkit --skill glyphgit clone --depth 1 https://github.com/yonatangross/orchestkitWrote 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/yonatangross/orchestkit/glyph)<a href="https://agentmods.dev/skills/yonatangross/orchestkit/glyph"><img src="https://agentmods.dev/badge/skills/yonatangross/orchestkit/glyph.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 | $0.00064 | $0.02381 |
| Opus 5 | $0.00032 | $0.01190 |
| Sonnet 5 | $0.00013 | $0.00476 |
| Haiku 4.5 | $0.00006 | $0.00238 |
Grade A, and why
glyph 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 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.
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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Glyph
Render the answer as ASCII art plus semantic emojis, inline, immediately. All output renders in a monospace terminal with no external tools.
Core principle: Encode information into structure, not decoration. Every diagram element should communicate something meaningful.
Execution (run this, do not ask first)
The whole point is speed, so there is no setup phase.
With no argument, the topic is the current conversation. Measured over a real 13-prompt session: zero asks supplied a self-contained topic, and the one direct invocation passed nothing at all. /ork:glyph on its own means "render where we are right now" — the open work, the decision just reached, the state of the thing being discussed. Render that; do not ask what to draw.
Given a topic (or the conversation, when none is given):
-
Render immediately. Do NOT call
AskUserQuestionto pick a format, do NOT callTaskCreate, do NOT spawn anAgent. Choose the form yourself from the topic shape and draw it. Asking first defeats the skill. -
Pick the form from the shape of the data, using the pattern library below:
Topic shape Form state / progress / health status box + bar meters A vs B, options, trade-offs comparison table or side-by-side boxes steps, pipeline, hand-offs left-to-right flow with ──▶containment, layers, layout nested boxes / tree ranked list, scores, counts table + bar meters over time sparkline or milestone track -
Emit inline in the reply. Never write a file unless the user asked for one. This is a chat answer, not an artifact.
-
Use the 12-emoji semantic set and box-drawing vocabulary defined in
rules/visual-style.md(shipped with this skill). Semantic, never decorative: an emoji must mean something (✅ pass, ❌ fail, ⚠️ risk, 🔴 blocked). -
Stay inside the budget: ≤ 12 visual lines, and ≤ 40% of the reply. Block count within that is free — two 5-line blocks are fine, four 10-line blocks are not. This skill renders on request, it does not render without limit (#3558). Full derivation of the numbers is in
rules/visual-style.md. -
State the point in prose first, in one or two sentences, then show the visual. The visual supports the answer; it is never the answer. If the reader has to parse a diagram to find out what happened, the reply failed.
-
Stay honest. If a number is unknown, print
?rather than inventing one. A confident-looking chart built on guesses is worse than prose.
What ships with it
12 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.
- CONTRIBUTING.md 4.6 KB
- primitives.json 2.6 KB
- references/page-route.md 7.9 KB
- rules/_sections.md 723 B
- rules/ascii-architecture.md 3.8 KB
- rules/ascii-diagrams.md 2.6 KB
- rules/status-glyph-vocabulary.md 2.1 KB
- rules/visual-style.md 7.2 KB
- templates/explainer.html 12 KB
- test-cases.json 6.7 KB
- tokens.json 2.3 KB
- tokens.schema.json 3.7 KB
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 · 216 lines · 64 tokens per session scan A 2b216db55855
glyph is a skill published in the GitHub repository yonatangross/orchestkit (228 stars, last pushed today), licensed MIT. It adds 64 tokens to every session and 2,381 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 2026-09-03.
Other skills, from other repositories
terminal-diagrams
Reference for drawing any diagram as plain monospace terminal text — box-drawing/ASCII, no external renderer. Read when work-preferences.md's trigger fires.
cocoplus-on
Activate Full Assist Mode — enables all CocoPlus features simultaneously: Memory Engine, Environment Inspector, Safety Gate (normal), Code Quality Advisor, Context Mode, and CocoMeter. Also triggers a background environment scan. Idempotent.
cocoplus-off
Deactivate Full Assist Mode — removes all CocoPlus feature flags. Data files (memory, meter history, grove patterns) are preserved. Idempotent.
wisdom-forget
Remove a must-keep CocoWisdom entry with rationale. Usage: $wisdom forget --id --rationale " ".
cocoplus-console
Launch CocoConsole, the CocoPlus 2.0 read-only local browser control plane. Use $cocoplus console, $cocoplus console status, or $cocoplus console stop.
screenpipe-api
Query the user's local and synced-device Screenpipe data via the REST API at localhost:3030. Use for screen activity, meetings, apps, productivity, other-device or cross-device history, media export, retranscription, or connected services.