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 skills/attemainio/dotnet-toolkit/dotnet-explorenpx skills add Attemainio/dotnet-toolkit --skill dotnet-exploregit clone --depth 1 https://github.com/Attemainio/dotnet-toolkitWhat 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 | $0.00104 | $0.01246 |
| Opus 5 | $0.00052 | $0.00623 |
| Sonnet 5 | $0.00021 | $0.00249 |
| Haiku 4.5 | $0.00010 | $0.00125 |
Grade A, and why
dotnet-explore 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 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.
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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Delegating the sweep to dotnet-explore
This plugin ships one read-only navigator subagent, dotnet-explore. It turns a prose task into the
symbols it is about: symbolIds, use sites, affected files, and how far a change would reach. It
never judges code and it cannot change it — the invoking agent decides what to do with the map.
Why delegate rather than fan out yourself. A wide search_index plus a get_references per
candidate is the single most expensive shape of read this server produces, and almost all of those
tokens are scaffolding you throw away once you know the answer. The agent pays them in its own
context and returns a report a fraction of the size.
When to invoke it — and when not to
Invoke it when the symbol set is genuinely unknown: an unfamiliar subsystem, "how would this feature land", "what breaks if I change this", a review or refactor whose boundary you cannot yet name.
Skip it when:
- The symbol is already known. A two-call lookup is not what this is for; use
dotnet-read. - The next step needs a
contentVersion. The agent is instructed never to report one — it is an edit lease that goes stale the moment anything moves, and a patch built on a relayed one getsstale_baseat best and a silent revert at worst. You fetch your own withget_symbol. - The answer is in a non-C# file.
.csproj,.json,.md,.editorconfigare out of its scope; it will say so and stop.
Step 0 — check readiness before launching
Call workspace_status yourself, before spawning. The agent checks too, but a cold or degraded
workspace wastes an entire agent run:
- Still loading, or
index_only→ semantic results are unavailable, not empty. Wait, or accept a syntax-tier map and say so. degraded(projects failed to load) → the map may be silently wrong. Fix the build andreload_workspacebefore spawning, or don't spawn.- Just did a
git pull/checkout/rebase, or added or deleted a.csfile →reload_workspace(scope: "all")first.
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 First seen · 88 lines · 0 tokens per session scan A 769809951cfe
dotnet-explore is a skill published in the GitHub repository Attemainio/dotnet-toolkit (2 stars, last pushed 6d ago), licensed MIT. It adds 104 tokens to every session and 1,246 once invoked, about $0.0005 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 skills, from other repositories
vela
Compiler-exact code search for .NET solutions - find where a symbol is defined, every reference to it, who calls it, and what a change would break. Covers C#, VB, Razor Pages, MVC views and Blazor components, which grep and every other code-intelligence tool miss. Deterministic, built on Roslyn, never modifies the…
dpg-migration
Migration logic for Azure SDK for .NET data-plane libraries migrating from AutoRest/Swagger to TypeSpec-based generation. Uses MCP tools from the generator-agent server for automated deterministic fixes.
csharp-azure-spector-coverage-gaps
Discovers and implements gaps in Spector test coverage for the Azure C# HTTP client emitter. Use when asked to find missing Spector scenarios, add Spector test coverage, or implement a specific Spector spec for the Azure C# emitter. Can also compare coverage between the Azure dashboard and the Standard (TypeSpec core)…
mgmt-review-comment-resolution
Resolve review comments on Azure management-plane .NET SDK PRs. Handles renaming types/properties, changing property types, and other API surface adjustments by updating TypeSpec client.tsp and regenerating.
mpg-migration
Handles Azure SDK for .NET management-plane migrations from AutoRest/Swagger to TypeSpec; use for MPG, mgmt migration, or Azure.ResourceManager. migration requests.
bump-mgmt-base-version
Bump the http-client-csharp base dependency version in http-client-csharp-mgmt. Updates emitter (npm) and generator (NuGet) references, rebuilds, and regenerates test projects.