OpenShell is a runtime for autonomous AI agents that executes them in sandboxed environments governed by declarative policies. It is used to restrict agents' access to files, credentials, data, and network resources, and the catalogue includes skills and workflows for operating and contributing to it.
Borrowing it
Nothing to install: this file belongs to NVIDIA/OpenShell. 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/NVIDIA/OpenShell/main/.agents/skills/tui-development/SKILL.mdgit clone --depth 1 https://github.com/NVIDIA/OpenShellWrote 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/nvidia/openshell/tui-development)<a href="https://agentmods.dev/skills/nvidia/openshell/tui-development"><img src="https://agentmods.dev/badge/skills/nvidia/openshell/tui-development/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/nvidia/openshell/tui-development"><img src="https://agentmods.dev/badge/skills/nvidia/openshell/tui-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 453 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00073 | $0.08385 |
| Opus 5.5 | $0.00029 | $0.03354 |
| Sonnet 5.5 | $0.00015 | $0.01677 |
| Haiku 4.5 | $0.00007 | $0.00839 |
Grade A, and why
tui-development 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 1mo 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 — 648 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenShell TUI Development Guide
Comprehensive reference for any agent working on the OpenShell TUI.
1. Overview
The OpenShell TUI is a ratatui-based terminal UI for the OpenShell platform. It provides a keyboard-driven interface for managing gateways, sandboxes, and logs — the same operations available via the openshell CLI, but with a live, interactive dashboard.
- Launched via:
openshell termormise run term - Crate:
crates/openshell-tui/ - Key dependencies:
ratatui(workspace version) — usesframe.area()for the drawable terminal areacrossterm(workspace version) — terminal backend and event pollingtonicwith TLS — gRPC client for the OpenShell gatewaytokio— async runtime for event loop, spawned tasks, and mpsc channelsopenshell-core— proto-generated types (OpenShellClient, request/response structs)openshell-bootstrap— gateway discovery (list_gateways())
- Theme: Adaptive dark/light via
Themestruct — NVIDIA-branded green accents. Controlled by--themeflag,OPENSHELL_THEMEenv var, or auto-detection.
2. Domain Object Hierarchy
The data model follows a strict hierarchy: Gateway > Workspace > Sandboxes/Providers/Settings > Logs.
Gateway (discovered via openshell_bootstrap::list_gateways())
├── Global Settings (fetched via GetGatewayConfig)
├── Global Policy indicator (fetched via ListSandboxPolicies global=true)
├── Workspaces (fetched via ListWorkspaces)
├── Provider Profiles (fetched via ListProviderProfiles, workspace-scoped)
├── Providers (fetched via ListProviders, workspace-scoped)
│ └── cached ProviderProfile (matched by type + workspace)
└── Sandboxes (fetched via ListSandboxes, workspace-scoped)
├── Policy (fetched via GetSandboxConfig)
├── Settings (effective settings with scope, from GetSandboxConfig)
├── Draft recommendations (fetched via GetDraftPolicy)
└── Logs (fetched via GetSandboxLogs + streamed via WatchSandbox)
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.
- 1mo ago Changed · -4 lines c90176dde6fe
- 1mo ago Changed · +2 lines 22c11ff412db
- 1mo ago Changed 59ac115e55eb
- 1mo ago Changed 77ee8b7ac1d2
- 1mo ago Changed · +5 lines 42decbfb06eb
- 1mo ago Changed · +4 lines 97da75c72a73
- 1mo ago Changed · +23 lines 9684154d88df
- 2mo ago Changed · +2 lines a2fb7f3e94b3
- 2mo ago Changed · -5 lines c52073370eb1
- 2mo ago First seen · 621 lines · 73 tokens per session scan A b73a80f86cef
tui-development is a skill published in the GitHub repository NVIDIA/OpenShell (21,172 stars, last pushed yesterday), licensed Apache-2.0. It adds 73 tokens to every session and 8,385 once invoked, about $0.0003 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 2026-08-30.
tui-development compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| tui-developmentNVIDIA/OpenShell | Skill | 21k | yesterday | Apache-2.0 | A | 73 | Claude Code, Codex |
| rust-patternsaffaan-m/ECC | Skill | 298k | 4d ago | MIT | A | 28 | Claude Code, Kiro |
| update-v8-versionopeninterpreter/openinterpreter | Skill | 69k | 2d ago | Apache-2.0 | A | 86 | Codex |
| dd-code-generationDataDog/pup | Skill | 1.0k | yesterday | Apache-2.0 | A | 16 | Claude Code |
| omh-rustrlaope/oh-my-hermes | Skill | 5.2k | today | MIT | A | 74 | Claude Code, Codex |
| swiftidebosun-ai/swiftide | Skill | 802 | yesterday | MIT | A | 47 | Claude Code, Codex |
| azure-keyvault-secrets-rustbenjaminasterA/antigravity-awesome-skills | Skill | 461 | yesterday | MIT | A | 0 | Claude Code, Codex |