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 covagashi/eplan-rag-mcp --skill eplan-developmentgit clone --depth 1 https://github.com/covagashi/eplan-rag-mcpWrote 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/covagashi/eplan-rag-mcp/eplan-development)<a href="https://agentmods.dev/skills/covagashi/eplan-rag-mcp/eplan-development"><img src="https://agentmods.dev/badge/skills/covagashi/eplan-rag-mcp/eplan-development.svg" alt="Measured on agentmods" height="20"></a>- 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 Data Exfiltration · line 43 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00084 | $0.01874 |
| Opus 5 | $0.00042 | $0.00937 |
| Sonnet 5 | $0.00017 | $0.00375 |
| Haiku 4.5 | $0.00008 | $0.00187 |
Grade A, and why
eplan-development 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 2d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST https://rag2027.covaga.xyz/search \ How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EPLAN Electric P8 Development
Comprehensive guide for developing with EPLAN Electric P8: scripting (C#), the EPLAN API, and remote automation. Distilled from working production code and curated examples.
The three development models
| Model | Runs | License | Use for |
|---|---|---|---|
| Scripting | Inside EPLAN (compiled on load, C# subset) | None extra | Automating actions, UI additions (ribbon), event hooks, file exports |
| API extension | Inside EPLAN (compiled DLL) or offline app | API license | Deep data access: parts DB, project object model, pages, properties |
| Remote Client | External process (WPF/console) driving a running EPLAN | RemoteClient DLLs | Orchestration apps, headless build pipelines, Cogineer generation |
Note: scripts CAN use some API namespaces (e.g. Eplan.EplApi.MasterData for the parts database) directly from a [Start] method — see references/api-data-access.md.
Reference files — read the one that matches the task
references/script-basics.md— Script structure, entry-point attributes ([Start],[DeclareAction],[DeclareEventHandler],[DeclareRegister]), deployment, scripting limitations.references/actions-reference.md— Executing actions withCommandLineInterpreter+ActionCallingContext; catalog of common actions (backup, export PDF, reports, labels, edit, selectionset…) with their parameters.references/core-classes.md—Progress,Decider,PathMapvariables,Settings,MultiLangString, ribbon/context menus,QuietModeStep, system messages (BaseException,SysMessagesCollection).references/api-data-access.md— Parts database (MDPartsManagement), reading and writing part properties (AddPart/RemovePart, theMDPropertyValueconstructor that doesn't exist, theAmbiguousMatchExceptionevery name-based property lookup hits), user-defined properties, multilanguage string parsing, resolving$(MD_DOCUMENTS)-style paths. Also: whyusing Eplan.EplApi.DataModel;/...HEServices;don't compile in scripts (CS0234) and how to reach that object model anyway.references/e3d-installation-spaces.md— The version-proof runtime-reflection recipe for reachingEplan.EplApi.DataModel/HEServicesfrom a script (LockingStep,FindType()assembly scanning, EPLAN 2027's...Netu-suffixed assemblies), applied to creating 3D installation spaces and inserting window macros headlessly.references/remoting.md—EplanRemoteClient: server discovery, dynamic ports, headless launch, version gotchas (2023 vs 2025), executing actions and scripts remotely, Cogineer generation from Excel.references/pitfalls.md— CRITICAL: the command-blocking issue (message loop / monitor thread),using/Disposediscipline, sequential execution model, error-handling rules, and the compile errors that masquerade as timeouts, including which C# each version's script engine actually accepts (#9).references/integration-patterns.md— Connecting EPLAN to the outside: HTTP servers, SignalR real-time messaging, forwarding EPLAN system errors to external services.
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.
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.
- 2d ago Changed · +1 lines efe710485bb5
- 4d ago Changed · +14 lines 8d4c3556d451
- 8d ago First seen · 57 lines · 84 tokens per session scan A 49e3dbfd5dde
eplan-development is a skill published in the GitHub repository covagashi/eplan-rag-mcp (83 stars, last pushed 3d ago), licensed MIT. It adds 84 tokens to every session and 1,874 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
addin-operations
TIA Portal Add-In development in Visual Studio Code: creating Add-In C# projects, adding Add-In templates, compiling and debugging Add-Ins, converting Add-Ins from older TIA Portal versions and configuring Add-In project parameters.
tia-plc-operations
C# Openness implementation of PLC software engineering.
tia-sivarc
C# TIA Portal Openness V21 automation for SIMATIC Visualization Architect (SiVArc): rule tables, rules and groups, library instances, tag/text definitions, tag member settings, expression resolution, layout exchange, definition upgrade, and generation.
tia-mac-module-builder
Siemens Modular Application Creator (MAC) and Module Builder development for TIA Portal V21. Use for TiaEquipmentModule lifecycle code, module models and use cases, generated/custom ownership, .tiares resources, packaging, and MAC qualification. Baseline: MAC V21.0.5 on .NET Framework 4.8.
tia-simatic-drives
Routed by tia-openness-roadmap. Handles drive-specific engineering: Startdrive, SINAMICS, SIMATIC Drive Controller, PROFIdrive integrated properties, drive telegrams, and integrated drive configuration. Always uses C# TIA Portal Openness.
tia-devices-general
C# Openness implementation of device-level operations.