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-teachgit 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-teach)<a href="https://agentmods.dev/commands/mathisk2095/jko-claude-plugins/dotnet-teach"><img src="https://agentmods.dev/badge/commands/mathisk2095/jko-claude-plugins/dotnet-teach.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 | $0.00029 | $0.00707 |
| Opus 5 | $0.00015 | $0.00353 |
| Sonnet 5 | $0.00006 | $0.00141 |
| Haiku 4.5 | $0.00003 | $0.00071 |
Grade A, and why
dotnet-teach 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 4d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
.NET Teach
Scan this .NET backend project, understand its real conventions, and persist the findings so future sessions start with the right context.
Step 1: Explore the Codebase
Before asking questions, thoroughly scan the project:
global.json,Directory.Build.props,Directory.Packages.props— SDK, language version, common props, package management*.sln,*.csproj— project structure, target frameworks, referencesProgram.csand service-registration extensions — host style, DI patterns, middleware/endpoints- AppHost project — whether
.NET Aspireis used and how strictly it is separated - Data access — EF Core, Dapper, raw SQL, migrations, transaction patterns
- Realtime — SignalR hubs, group management, connection state strategy
- Background work —
BackgroundService, channels, queue abstractions - Logging/observability — ILogger, Serilog, OpenTelemetry, correlation patterns
- Tests — unit/integration/API test projects and tools
- Existing
CLAUDE.md— preserve or extend existing project guidance
Note what is clearly inferable and what remains uncertain.
Step 2: Ask Clarifying Questions
Ask only what the codebase cannot answer.
Project Context
- Is this backend a modular monolith, product suite, or service in a larger ecosystem?
- Is AppHost only for local orchestration, or part of the team's normal distributed-dev workflow?
- Any hard latency, throughput, or reliability requirements?
Conventions
- Is the preferred endpoint style minimal APIs, controllers, or mixed?
- Are repositories required everywhere, or only at selected boundaries?
- Are vertical slices preferred over strict layer buckets?
Quality Rules
- Any strict rules for file size, interface usage, or architecture layering?
- Any data or messaging rules that all contributors must follow?
- Any specific DI lifetime or SignalR policies?
Skip questions where the answer is already evident from the code.
Step 3: Write .NET Backend Context
Synthesize findings into a ## .NET Backend Conventions section:
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.
- 4d ago First seen · 91 lines · 29 tokens per session scan A 91a8324f9af9
dotnet-teach is a command published in the GitHub repository mathisk2095/jko-claude-plugins (3 stars, last pushed 6d ago), licensed MIT. It adds 29 tokens to every session and 707 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
ccc-compound
Post-task learning capture — extract patterns, corrections, and decisions to compound productivity.
code-review-teach
Educational code review that teaches while reviewing. Provides constructive feedback, explains best practices, discusses trade-offs, and helps developers improve their coding skills.
business-logic-map
Extract and map all business logic, rules, and workflows from the codebase.
review
Cold re-quiz on code that already shipped — your own session commits, not the change in front of you.
lead
Tech lead: classify, quiz, ticket on the owning repo, dispatch. Do not implement.
study-help
Explain the agentic-study-environment harness — everything it offers, or a specific skill, domain overlay, session type, or convention if you name one.