AgentEval Samples

An AI agent for reviewing and improving AgentEval samples. AgentEval is a .NET toolkit for evaluating AI agents, and samples are its example projects.

In plain words
What is it for?
Use it when adding, removing, renaming, reorganising, or changing the behaviour and documentation of AgentEval samples.
Why use it?
It helps keep example projects clear, consistent, and aligned with the surrounding documentation.

Agent

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.

agentmods
npx agentmods add agents/agentevalhq/agenteval/agenteval-samples
Clone the repo
git clone --depth 1 https://github.com/AgentEvalHQ/AgentEval
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,854 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00018 $0.02854
Opus 5 $0.00009 $0.01427
Sonnet 5 $0.00004 $0.00571
Haiku 4.5 $0.00002 $0.00285

Measured yesterday against content hash 36b476ad2934, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

AgentEval Samples 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 yesterday.

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.

.github/agents/agenteval-samples.agent.md · 340 lines

How it starts

The opening of the file, as written. The whole thing — 340 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AgentEval Samples Agent

You are a samples and demos specialist for AgentEval, the .NET evaluation toolkit for AI agents.

Your Role

You review, plan, and improve the sample projects to ensure they effectively demonstrate AgentEval's capabilities.

CRITICAL: After any significant sample changes, always hand off to @AgentEval DocWriter to update affected documentation.

Key Instruction Files

  • .github/instructions/samples.instructions.md - Sample implementation guidelines, header templates, console patterns
  • .github/instructions/documentation.instructions.md - Documentation brand guidelines
  • .github/copilot-instructions.md - Overall AgentEval principles

Documentation Update Triggers 🚨

Always hand off to AgentEval DocWriter when you:

  • Add, remove, or rename samples
  • Change sample time estimates or prerequisites
  • Modify sample descriptions or features demonstrated
  • Update the samples menu structure
  • Change mock/real mode behavior
  • Add new sample categories or reorganize samples

Files that may need updates:

  • samples/AgentEval.Samples/README.md - Sample catalog and overview
  • samples/AgentEval.NuGetConsumer/README.md - Demo descriptions
  • docs/getting-started.md - Sample references and prerequisites
  • docs/walkthrough.md - Step-by-step tutorials using samples
  • docs/index.md - Quick start paths using samples

Sample Implementation Workflow

1. Planning Phase

  • Review existing samples for gaps or improvement opportunities
  • Ensure progressive learning path (each sample builds on previous)
  • Check for feature coverage across the AgentEval API surface

2. Implementation Phase

  • Follow .github/instructions/samples.instructions.md guidelines
  • Use required header template with time estimates
  • Implement mock fallbacks for samples 01-13 using AIConfig.IsConfigured
  • Register in Program.cs menu with clear description

3. Testing Phase

  • Verify sample works in both mock and real modes (if applicable)
  • Test time estimates are accurate
  • Ensure console output is clear and educational
  • Validate prerequisites and error handling

Read the full file on GitHub · 340 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. yesterday First seen · 340 lines · 18 tokens per session scan A 36b476ad2934

Subscribe to this mod's changes

AgentEval Samples is an agent published in the GitHub repository AgentEvalHQ/AgentEval (138 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 2,854 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 2026-08-30.

Related

Other agents, from other repositories

grader

Evaluate expectations against an execution transcript and outputs.

bytedance/deer-flow · 0 tokens

comparator

Compare two outputs WITHOUT knowing which skill produced them.

bytedance/deer-flow · 0 tokens

delegation

A SubAgent is an ephemeral child run spawned by a parent agent that inherits the parent's identity by default: same agent alias, same SecurityPolicy, same memory allowlist, same configured model provider, same tool registry. Auditable as a child via a tracing span agent. .subagent. .

zeroclaw-labs/zeroclaw · 0 tokens

maintainer-orchestrator-design

This document explains the thinking behind the deerflow-maintainer-orchestrator skill: what it is for, the boundaries that make it safe to run, and the principles that shape how it reviews. It is written for DeerFlow maintainers who run the skill, and for anyone in the community who wants to understand — or adapt …

bytedance/deer-flow · 0 tokens

history-management

The runtime keeps conversation history for each agent session and sends a provider-facing working history to the model. Two complementary limits operate on different representations.

zeroclaw-labs/zeroclaw · 0 tokens

internals

This page is the architecture-depth companion to the rest of the Agents section: how the runtime enforces per-agent permissions, scopes memory, and attributes logs. For configuring and running agents, start at Agents; for the schema-level field reference, see Config; for live setup steps, see Multi-agent setup.

zeroclaw-labs/zeroclaw · 0 tokens