Borrowing it
Nothing to install: this file belongs to sergeyzwezdin/huba. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sergeyzwezdin/huba/main/.claude/skills/opentui-developer/SKILL.mdgit clone --depth 1 https://github.com/sergeyzwezdin/hubaWrote 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/sergeyzwezdin/huba/opentui-developer)<a href="https://agentmods.dev/skills/sergeyzwezdin/huba/opentui-developer"><img src="https://agentmods.dev/badge/skills/sergeyzwezdin/huba/opentui-developer/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/sergeyzwezdin/huba/opentui-developer"><img src="https://agentmods.dev/badge/skills/sergeyzwezdin/huba/opentui-developer.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 | $0.00046 | $0.01012 |
| Opus 5.5 | $0.00018 | $0.00405 |
| Sonnet 5.5 | $0.00009 | $0.00202 |
| Haiku 4.5 | $0.00005 | $0.00101 |
Grade A, and why
opentui 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 2mo 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenTUI Platform Skill
How to Read This Skill
Each domain has a REFERENCE.md index that maps sub-files to topics. Start with the index, then load only what's needed.
| Domain | Entry Point | When to Use |
|---|---|---|
| Core | ./references/core/REFERENCE.md |
Imperative API, low-level control |
| React | ./references/react/REFERENCE.md |
Declarative UI, hooks, JSX |
| Layout | ./references/layout/REFERENCE.md |
Flexbox layout, positioning |
| Components | ./references/components/REFERENCE.md |
Component-by-category reference |
| Keyboard | ./references/keyboard/REFERENCE.md |
Key events, shortcuts, clipboard |
| Animation | ./references/animation/REFERENCE.md |
Timeline animations |
| Testing | ./references/testing/REFERENCE.md |
Snapshot and interaction testing |
Quick Decision Trees
"I need to display content"
Display content?
├─ Plain or styled text -> components/text-basic.md
├─ ASCII art banner/title -> components/text-extras.md
├─ Container with borders/background -> components/containers-box.md
├─ Scrollable content area -> components/containers-scrollbox.md
├─ Code with syntax highlighting -> components/code-syntax.md
├─ Diff viewer (unified/split) -> components/diff.md
└─ Markdown content (streaming) -> components/code-syntax.md (markdown)
"I need user input"
User input?
├─ Single-line text field -> components/inputs-text.md
├─ Multi-line text editor -> components/inputs-text.md (textarea)
├─ Select from a list (built-in) -> components/inputs-select.md
├─ Custom-rendered list/select -> components/inputs-select.md (BaseSelectRenderable)
├─ Tab-based selection -> components/inputs-select.md (tab-select)
└─ Custom keyboard handling -> keyboard/REFERENCE.md
"I need layout/positioning"
Layout?
├─ Flexbox rows/columns -> layout/REFERENCE.md + layout/flex.md
├─ Absolute positioning -> layout/positioning.md
├─ Responsive to terminal -> layout/patterns-app.md
├─ Centering content -> layout/patterns-advanced.md
└─ Common app layouts -> layout/patterns-app.md
What ships with it
60 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.
- references/animation/easing.md 1.6 KB
- references/animation/patterns.md 2.6 KB
- references/animation/REFERENCE.md 1.6 KB
- references/animation/timeline.md 1.8 KB
- references/components/code-diff.md 1.1 KB
- references/components/code-syntax.md 4.0 KB
- references/components/containers-box.md 2.9 KB
- references/components/containers-scrollbox.md 3.5 KB
- references/components/containers.md 1.2 KB
- references/components/diff.md 1.9 KB
- references/components/inputs-select.md 7.7 KB
- references/components/inputs-text.md 3.3 KB
- references/components/inputs.md 876 B
- references/components/REFERENCE.md 3.7 KB
- references/components/text-basic.md 2.6 KB
- references/components/text-display.md 818 B
- references/components/text-extras.md 2.4 KB
- references/core/api.md 1.5 KB
- references/core/colors.md 1.9 KB
- references/core/configuration.md 4.3 KB
- references/core/constructs.md 1.6 KB
- references/core/gotchas-advanced.md 2.9 KB
- references/core/gotchas-basics.md 3.4 KB
- references/core/gotchas.md 993 B
- references/core/patterns-composition.md 2.4 KB
- references/core/patterns-events.md 1.6 KB
- references/core/patterns-focus.md 2.4 KB
- references/core/patterns-lifecycle.md 1.9 KB
- references/core/patterns.md 1.1 KB
- references/core/REFERENCE.md 4.1 KB
- references/core/renderables.md 4.1 KB
- references/core/renderer.md 2.2 KB
- references/keyboard/clipboard.md 967 B
- references/keyboard/keys.md 1.7 KB
- references/keyboard/patterns.md 2.3 KB
- references/keyboard/REFERENCE.md 1.2 KB
- references/layout/dimensions.md 1.4 KB
- references/layout/flex.md 2.7 KB
- references/layout/patterns-advanced.md 2.2 KB
- references/layout/patterns-app.md 2.5 KB
- references/layout/patterns.md 945 B
- references/layout/positioning.md 1.4 KB
- references/layout/REFERENCE.md 1.9 KB
- references/react/api-components.md 3.1 KB
- references/react/api-hooks.md 2.7 KB
- references/react/api.md 1.6 KB
- references/react/configuration-advanced.md 2.7 KB
- references/react/configuration-setup.md 3.2 KB
- references/react/configuration.md 786 B
- references/react/gotchas-runtime.md 4.0 KB
- references/react/gotchas-setup.md 3.6 KB
- references/react/gotchas.md 942 B
- references/react/patterns-forms.md 2.4 KB
- references/react/patterns-keyboard.md 2.9 KB
- references/react/patterns-responsive.md 1.9 KB
- references/react/patterns-settings.md 2.8 KB
- references/react/patterns-state.md 4.1 KB
- references/react/patterns-theming.md 4.2 KB
- references/react/patterns-toast.md 2.0 KB
- references/react/patterns.md 1.2 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.
- 2mo ago First seen · 123 lines · 46 tokens per session scan A 329c8f88a573
opentui is a skill published in the GitHub repository sergeyzwezdin/huba (10 stars, last pushed 7mo ago), licensed MIT. It adds 46 tokens to every session and 1,012 once invoked, about $0.0002 per session on Opus 5.5. 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
compliance-frameworks
Swiss financial regulatory compliance — FINMA, GwG/AML/KYC, FIDLEG/FINIG licensing, BankG, crypto/DLT regulation, cross-border obligations (AEOI/CRS, FATCA). Trigger when: user asks about FINMA licensing, AML/KYC compliance, financial services cross-border, crypto regulation, or fintech data processing. Do NOT trigger…
data-protection-law
Swiss data protection — nDSG/FADP framework, GDPR adequacy, cantonal DP laws (IDG/KDSG/LIPAD), DSFA/DPIA, cross-border transfers. Trigger when: user asks about nDSG/GDPR compliance, DPAs, data transfers, DPIA, data subject rights, or references FDPIC/nDSG/FADP. Do NOT trigger for: fintech regulatory compliance (use…
swiss-legal-research
Swiss legal research and jurisdiction resolution — searches BGE/ATF/DTF precedents, interprets federal and cantonal statutes, resolves federal vs. cantonal jurisdiction, and produces verified multi-lingual legal analysis. Trigger when: a user asks what the law says, requests precedents, needs statute interpretation…
swiss-legal-strategy
Swiss legal strategy — case strength, risk probability, cost-benefit, settlement/BATNA, and ADR assessment across ZPO/StPO/VwVG proceedings. Trigger when: user needs litigation viability, settle-or-sue decision, procedural options, or strategy memo. Uses entscheidsuche MCP for precedent-based probability. Do NOT…
adversarial-analysis
Adversarial stress test — three agents (Advocate FOR, Adversary AGAINST, Judicial synthesis with probability). Trigger when: user wants to stress-test a position, check weaknesses before filing, or requests adversarial review. Also option '4' in /legal menu. Do NOT trigger for: initial research (swiss-legal-research)…
legal-evaluator
Verdict engine — judges artifacts against a Goal Record using MCP verification tools. Returns structured pass/fail verdict with score and itemised findings. Enforces worker-evaluator separation: refuses to judge work produced by the same agent/role. Used by /legal-loop. Do NOT trigger for: producing work (drafting…