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 commands/mathisk2095/jko-claude-plugins/dotnet-structuregit clone --depth 1 https://github.com/mathisk2095/jko-claude-pluginsWrote 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/commands/mathisk2095/jko-claude-plugins/dotnet-structure)<a href="https://agentmods.dev/commands/mathisk2095/jko-claude-plugins/dotnet-structure"><img src="https://agentmods.dev/badge/commands/mathisk2095/jko-claude-plugins/dotnet-structure.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 | $0.00024 | $0.00466 |
| Opus 5 | $0.00012 | $0.00233 |
| Sonnet 5 | $0.00005 | $0.00093 |
| Haiku 4.5 | $0.00002 | $0.00047 |
Grade A, and why
dotnet-structure 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 3d 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.
What it actually says
Analyze the .NET backend structure. If $ARGUMENTS is provided, analyze that solution, directory, or project. Otherwise auto-detect the main backend solution.
First: Use the dotnet-backend-expert skill. Read references/project-structure.md and references/architecture.md.
Analysis Steps
- Map the solution:
- list
*.slnand*.csproj - classify projects as API/host, AppHost, contracts, application, domain, infrastructure, workers, tests
- detect whether the codebase is layered, vertical slice, modular monolith, or tangled
- list
- File size audit:
- flag
.csfiles over 300 lines as split candidates - flag
.csfiles over 500 lines as urgent - suggest the split by responsibility, not by arbitrary regions
- flag
- Project boundary audit:
- domain should not depend on infrastructure or host projects
- contracts should stay transport-safe
- AppHost should orchestrate, not contain business rules
- Folder organization audit:
- check for one major type per file
- check for feature grouping versus giant technical buckets
- check whether endpoints, services, repositories, entities, and contracts are easy to locate
- Missing pieces:
- missing contracts project or folder
- missing application/service boundary
- missing test projects
- missing composition root extensions
Output
Current Structure
Show a tree with project purpose and notable line counts.
Structure Score: X/10
Explain the score briefly.
Issues Found
Order by impact. For each issue include the exact project/file and the recommended move, split, or create action.
Recommended Target Layout
If a change is needed, show the ideal target shape for this backend.
Migration Steps
Give a safe incremental path that keeps the app working at each step.
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.
- 3d ago First seen · 57 lines · 24 tokens per session scan A 5b1458bdaa03
dotnet-structure is a command published in the GitHub repository mathisk2095/jko-claude-plugins (3 stars, last pushed 5d ago), licensed MIT. It adds 24 tokens to every session and 466 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 2026-08-31.
Other commands, from other repositories
profile
Coordinate a reproducible Java profiling and optimization lifecycle.
dumpmt
Displays details about method tables (MethodTable).
roast
Convene a 5-persona adversarial council (Contrarian, Expansionist, Logician, Researcher, Buyer) to pressure-test an idea, then deliver one GO / RESHAPE / KILL verdict plus the cheapest 48-hour test to de-risk it. Enforces Law 1 (Research Before Executing).
standup
Dev standup — open Linear tickets grouped by in-flight, top priority, and backlog.
export
Export a conversation to Notion or Feishu.
test
Run .NET TDD workflow — write failing xUnit/MSTest tests, implement, verify. For bugs, use the Prove-It pattern.