dnp-fable-advisor

dnp-fable-advisor is an agent for Claude Code from zdanovichnick/dotnet-pilot. It costs 80 tokens per session (1,260 once invoked), scanned A, original, MIT.

A senior .NET advisor that gives written guidance but does not edit code. It can advise before difficult work, help when an implementation is stuck, or check whether another agent's claim matches the code.

In plain words
What is it for?
Use it to shape interfaces and cross-layer contracts, unblock a looping implementation, or review a suspected defect or architectural decision.
Why use it?
It provides a second technical judgment at important decision points without taking over implementation.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Part of the dotnet-pilot plugin — 16 skills, 15 agents, 3 hooks, 1 MCP server shipped together

Good fit Use it to shape interfaces and cross-layer contracts, unblock a looping implementation, or review a suspected defect or architectural decision.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/zdanovichnick/dotnet-pilot/dnp-fable-advisor
Install

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.

Clone the repo
git clone --depth 1 https://github.com/zdanovichnick/dotnet-pilot

Made for: Claude Code.

Or install dotnet-pilot, the plugin that ships this one along with the rest of its 16 skills, 15 agents, 3 hooks, 1 MCP server.

Wrote 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.

agentmods badge for dnp-fable-advisor

README.md
[![agentmods](https://agentmods.dev/badge/agents/zdanovichnick/dotnet-pilot/dnp-fable-advisor/github.svg)](https://agentmods.dev/agents/zdanovichnick/dotnet-pilot/dnp-fable-advisor)
Your own site
<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.

agentmods 80×15 button for dnp-fable-advisor

Your own site · 80×15
<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>
Per session 80 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,260 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 8d ago against content hash 6de7983fdea9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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.

agents/dnp-fable-advisor.md · 100 lines

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.

Read the full file on GitHub · 100 lines

Changes

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.

  1. 8d ago First seen · 100 lines · 80 tokens per session scan A 6de7983fdea9

Subscribe to this mod's changes

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.