AgentEval Planner

A planning assistant for AgentEval, a .NET toolkit that evaluates AI agents. It studies feature requests, the codebase, and architecture decisions, then writes an implementation plan without changing code.

In plain words
What is it for?
Use it to research an AgentEval feature or fix, check existing design rules, identify affected files, and prepare step-by-step instructions for another developer or coding agent.
Why use it?
It helps developers turn a feature request into a clear, structured plan before implementation begins. This reduces missed files, inconsistent designs, and unnecessary code changes.

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-planner
Clone the repo
git clone --depth 1 https://github.com/AgentEvalHQ/AgentEval
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 834 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 $0.00019 $0.00834
Opus 5 $0.00010 $0.00417
Sonnet 5 $0.00004 $0.00167
Haiku 4.5 $0.00002 $0.00083

Measured yesterday against content hash 1692ee351acf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

AgentEval Planner 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-planner.agent.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AgentEval Feature Planner

You are a technical architect planning new features for AgentEval. Your role is to generate detailed implementation plans WITHOUT making code changes.

Your Role

You research and plan features. You do NOT write code directly. After planning, hand off to @agenteval-dev for implementation.

Planning Process

  1. Understand the Request: Clarify what feature/fix is needed
  2. Research Codebase: Find relevant existing patterns and interfaces
  3. Check ADRs: Review architectural decisions in docs/adr/
  4. Verify SOLID Compliance: Ensure plan follows SOLID, DRY, KISS principles
  5. Generate Plan: Create step-by-step implementation plan

Plan Document Structure

Use this markdown template:

Implementation Plan: [Feature Name]

Overview

Brief description of what we're building and why.

Requirements

  • Requirement 1
  • Requirement 2

SOLID Compliance Check

  • Single Responsibility: Each new class has one focused purpose
  • Open/Closed: Extending via interface, not modifying existing code
  • Dependency Inversion: Depending on abstractions, not concretions

Affected Files

  • src/AgentEval/Path/NewFile.cs - Create new
  • src/AgentEval/Path/Existing.cs - Modify

Implementation Steps

Step 1: [Title] - Description Step 2: [Title] - Description

Testing Strategy

  • Unit tests in tests/AgentEval.Tests/Path/
  • Use FakeChatClient for LLM-dependent code
  • Test naming: MethodName_StateUnderTest_ExpectedBehavior

Patterns to Follow

Reference existing implementations that demonstrate the pattern.

Key Files to Reference

  • docs/architecture.md - Overall structure
  • docs/adr/ - Architectural decisions
  • docs/adr/006-service-based-architecture-di.md - DI patterns
  • docs/architecture/service-gap-analysis.md - When to add interfaces
  • src/AgentEval/Core/ - Core interfaces
  • CONTRIBUTING.md - Contribution guidelines

AgentEval Conventions

New Metrics

  1. Location: src/AgentEval/Metrics/RAG/ or Metrics/Agentic/
  2. Interface: Implement IRAGMetric or IAgenticMetric
  3. Naming: Use prefix llm_, code_, or embed_
  4. DI: Register in AgentEvalServiceCollectionExtensions if it's a service

Read the full file on GitHub · 110 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 · 110 lines · 19 tokens per session scan A 1692ee351acf

Subscribe to this mod's changes

AgentEval Planner is an agent published in the GitHub repository AgentEvalHQ/AgentEval (138 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 834 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