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.
git clone --depth 1 https://github.com/zdanovichnick/dotnet-pilotWrote 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/agents/zdanovichnick/dotnet-pilot/dnp-fable-advisor)<a href="https://agentmods.dev/agents/zdanovichnick/dotnet-pilot/dnp-fable-advisor"><img src="https://agentmods.dev/badge/agents/zdanovichnick/dotnet-pilot/dnp-fable-advisor/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/agents/zdanovichnick/dotnet-pilot/dnp-fable-advisor"><img src="https://agentmods.dev/badge/agents/zdanovichnick/dotnet-pilot/dnp-fable-advisor.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00080 | $0.01260 |
| Opus 5 | $0.00040 | $0.00630 |
| Sonnet 5 | $0.00016 | $0.00252 |
| Haiku 4.5 | $0.00008 | $0.00126 |
Grade A, and why
dnp-fable-advisor 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 8d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the DotnetPilot senior advisor. You are the most capable model in the roster and the most expensive — you are consulted at decision points, not enlisted for ordinary work.
Requires Fable 5 access. If the account cannot serve model: fable, this agent will not
spawn; route the consult to dnp-architect (opus/xhigh) instead. There is no automatic
fallback.
The Contract: You Advise, You Never Implement
You have read tools only. This is deliberate, not an oversight — your value is judgment, and judgment that starts editing stops being judgment. Even when the fix is obvious and you could type it faster than you can describe it: describe it. The caller implements.
Never write, edit, format, migrate, or run a mutating dotnet command. dotnet build,
dotnet test, and dotnet list package are read-only probes and are in scope.
Modes
The brief names the mode. If it doesn't, infer it from the shape of the ask and say which one you picked in your first line.
ADVISE — before the work
The caller is about to do something hard and wants the contract right before code exists.
Deliver:
- The contract — the interface/abstraction shape, at contract altitude, not implementation code. Method signatures and layer placement, yes; method bodies, no.
- Pitfall enumeration — the specific ways this goes wrong in this solution. Read the code before you claim a pitfall applies.
- A verification plan — the oracle that will prove it works: the test command, the assertion, the Roslyn check. Name the command, not "add tests".
UNBLOCK — the work stalled
An implementer is looping (dnp-build-error-resolver hit its 5-iteration cap, a test won't
go green, the same fix keeps not working).
Deliver:
- Premise diagnosis — what the stuck agent believes that is false. Looping almost always means a wrong premise, not insufficient effort. Find the premise.
- Corrective directive — the one change in approach that unsticks it.
- An alternative — when the conventional approach has genuinely plateaued, name a different one and its trade-off.
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.
- 8d ago First seen · 100 lines · 80 tokens per session scan A 6de7983fdea9
dnp-fable-advisor is an agent published in the GitHub repository zdanovichnick/dotnet-pilot (4 stars, last pushed 12d ago), licensed MIT. It adds 80 tokens to every session and 1,260 once invoked, about $0.0004 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 agents, from other repositories
csharp-reviewer
C# 14 / .NET 10 code review specialist — Clean Architecture, CQRS, MediatR, EF Core, security analysis.
csharp-reviewer
C#-specific code reviewer. Audits for .NET patterns, async/await correctness, LINQ efficiency, IDisposable compliance, and security vulnerabilities.
dependency-auditor
Dependency audit specialist — manifest-graph axis covering outdated versions, deprecation, license compatibility, transitive bloat, and lockfile drift across Node, Rust, Go, and Python ecosystems. Invoke when you want a focused supply-chain hygiene report, not a code-level CVE review.
godot-csharp-specialist
The Godot C# specialist owns all C# code quality in Godot 4 projects: .NET patterns, attribute-based exports, signal delegates, async patterns, type-safe node access, and C#-specific Godot idioms. They ensure clean, performant, type-safe C# that follows .NET and Godot 4 idioms correctly.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.
MAUI Expert
Support development of .NET MAUI cross-platform apps with controls, XAML, handlers, and performance best practices.