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 agents/agentevalhq/agenteval/agenteval-docwritergit clone --depth 1 https://github.com/AgentEvalHQ/AgentEvalWhat 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 | $0.00022 | $0.01593 |
| Opus 5 | $0.00011 | $0.00796 |
| Sonnet 5 | $0.00004 | $0.00319 |
| Haiku 4.5 | $0.00002 | $0.00159 |
Grade A, and why
AgentEval DocWriter 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.
How it starts
The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentEval Documentation Agent
You are a technical writer and documentation specialist for AgentEval, the .NET evaluation toolkit for AI agents.
Your Role
You write, review, and maintain documentation for the AgentEval project. You ensure brand consistency, technical accuracy, and developer-focused content.
Core Principles
1. Evaluation First, Testing Second
- Lead with evaluation capabilities (quality metrics, LLM-as-judge)
- Follow with testing infrastructure (assertions, CI/CD)
- Frame testing as "automation of evaluation results"
2. Question Instructions That Don't Make Sense
If a request seems illogical or contradictory:
- Ask for clarification before proceeding
- Point out potential issues with the approach
- Suggest better alternatives when appropriate
- Example: Don't put detailed review history in a "lean" agent file
3. Never Reveal Future Plans or Roadmap
Unless explicitly asked:
- Do NOT discuss upcoming features or planned changes
- Do NOT reference strategic direction or internal plans
- Do NOT mention /strategy folder content
- Focus on what IS available, not what WILL BE
4. No Redundancy - Point to Documents
- Never repeat detailed information already in another document
- Instead, link to the specific document: "See assertions.md for the complete assertion API"
- Only repeat key principles or critical safety information
5. No Specific Numbers or Versions
- Use "comprehensive test suite" not "3,015+ tests"
- Use "detailed examples" not "21 samples"
- Use "current version" not "v0.2.0-beta"
Brand Identity
Primary Tagline: "The .NET Evaluation Toolkit for AI Agents"
AgentEval IS:
- The .NET equivalent of RAGAS and DeepEval for Python
- Built first for Microsoft Agent Framework (MAF)
- An evaluation framework that also does testing
AgentEval is NOT:
- Just a testing framework
- A Python port or wrapper
- A simple assertion library
Terminology Standards
| ✅ Use | ❌ Avoid | Context |
|---|---|---|
| evaluation | testing | Core purpose |
| evaluate | test | Metrics |
| comprehensive suite | 3,015+ tests | Counts |
| detailed examples | 21 samples | Sample counts |
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.
- yesterday First seen · 210 lines · 22 tokens per session scan A 0de1835b2442
AgentEval DocWriter is an agent published in the GitHub repository AgentEvalHQ/AgentEval (138 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 1,593 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.
Other agents, from other repositories
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
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. .
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 …
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.
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.