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 skills add Czarnak/totally-integrated-claude --skill tia-devices-generalgit clone --depth 1 https://github.com/Czarnak/totally-integrated-claudeWrote 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/czarnak/totally-integrated-claude/tia-devices-general)<a href="https://agentmods.dev/skills/czarnak/totally-integrated-claude/tia-devices-general"><img src="https://agentmods.dev/badge/skills/czarnak/totally-integrated-claude/tia-devices-general/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/czarnak/totally-integrated-claude/tia-devices-general"><img src="https://agentmods.dev/badge/skills/czarnak/totally-integrated-claude/tia-devices-general.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00015 | $0.00606 |
| Opus 5 | $0.00008 | $0.00303 |
| Sonnet 5 | $0.00003 | $0.00121 |
| Haiku 4.5 | $0.00002 | $0.00061 |
Grade A, and why
tia-devices-general 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 12d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tia-devices-general
Scope
Device-level engineering — full C# Openness implementation.
When the roadmap routes here, the entire solution is C#.
Do not mix with Python wrapper calls.
Always load tia-csharp-common first (done by roadmap).
Reference files
Load ONLY the reference file(s) relevant to the task. Do not load all files at once.
| Reference file | Load when the task involves |
|---|---|
references/device-enumeration.md |
Listing, finding, or iterating devices; device groups; ungrouped devices; navigating DeviceItems. |
references/device-creation.md |
Creating or deleting devices; understanding TypeIdentifier formats (OrderNumber, GSD, System). |
references/device-attributes.md |
Reading/writing basic device or device-item attributes; using GsdDevice service; managing Application IDs (CustomIdentityProvider). |
references/hardware-parameters.md |
Setting specific hardware parameters via SetAttribute (e.g., IO addresses, diagnostic settings, module-specific enums). |
references/software-container.md |
Accessing PlcSoftware or HmiTarget from a device; using the SoftwareContainer service. |
references/device-item-operations.md |
Plugging, moving, copying, or deleting device items/modules; changing device/module types; hardware catalog queries. |
references/device-item-interfaces.md |
NetworkInterface service; IOController/IOConnector attributes; hardware identifiers; managing addresses and channels. |
references/networks-and-connections.md |
Opening hardware/network editors; querying targets from a network perspective; address object attributes. |
For tasks spanning multiple areas, load all relevant reference files before generating code.
Execution pattern
- Access
Project.Devicescomposition (orDeviceGroups/UngroupedDevicesGroup) - Resolve the exact existing object or exact
TypeIdentifier; never select the first catalog/device/device-item match - Before create, plug, move, copy, change-type, attribute write, import, or delete, obtain explicit authorization for the exact project, object identity, and requested mutation
- Navigate the complete recursive
DeviceItemhierarchy as needed - Access
SoftwareContainerviaGetService<SoftwareContainer>()when PLC, classic HMI, or Unified HMI software is needed - Put supported project mutations in
ExclusiveAccessplus a transaction and allow exceptions to roll it back (seetia-csharp-common) - Use
ICompilablefor hardware or software compile and inspect the fullCompilerResult(seetia-project-general/references/compile.md) - Do not save when selection is ambiguous, a service is unavailable, a mutation reports an error, or compile/consistency validation fails
What ships with it
8 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/device-attributes.md 13 KB
- references/device-creation.md 6.8 KB
- references/device-enumeration.md 7.9 KB
- references/device-item-interfaces.md 19 KB
- references/device-item-operations.md 17 KB
- references/hardware-parameters.md 125 KB
- references/networks-and-connections.md 21 KB
- references/software-container.md 5.1 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.
- 12d ago First seen · 49 lines · 15 tokens per session scan A a6750aea2969
tia-devices-general is a skill published in the GitHub repository Czarnak/totally-integrated-claude (57 stars, last pushed 27d ago), licensed MIT. It adds 15 tokens to every session and 606 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
bootstrap-solution
Bootstrap or guide a reproducible .NET solution with explicit F# or C# language choice, SDK selection, project layout, test project setup, and initial validation commands.
build-csharp-project
Build or modify idiomatic C# .NET projects using nullable-aware APIs, records/classes, async/task behavior, analyzer conventions, tests, and repo-local validation.
csharp-developer
Use when building C# applications with .NET 8+, ASP.NET Core APIs, or Blazor web apps. Builds REST APIs using minimal or controller-based routing, configures database access with Entity Framework Core, implements async patterns and cancellation, structures applications with CQRS via MediatR, and scaffolds Blazor…
dotnet-core-expert
Use when building .NET 8 applications with minimal APIs, clean architecture, or cloud-native microservices. Invoke for Entity Framework Core, CQRS with MediatR, JWT authentication, AOT compilation.
phx-deps-audit
Audit Hex deps for supply-chain security risk — bidi chars, compile-time exec, maintainer changes, typosquats, CVEs. Use after mix deps.update, when checking if a package upgrade is safe, or reviewing mix.lock PR diffs.
cran-extrachecks
Prepare R packages for CRAN submission by checking for common ad-hoc requirements not caught by devtools::check(). Use when: (1) Preparing a package for first CRAN release, (2) Preparing a package update for CRAN resubmission, (3) Reviewing a package to ensure CRAN compliance, (4) Responding to CRAN reviewer feedback.…