agentv-bench

A workflow for testing AI agents repeatedly and improving them from the results. An evaluation is a set of test tasks used to measure whether an agent behaves as intended.

In plain words
What is it for?
Use it to create or run AgentV benchmarks, compare agent outputs, debug failures, analyze recorded sessions, and optimize agents over multiple iterations.
Why use it?
It replaces guesswork with a repeatable cycle of writing tests, running the agent, reviewing failures, and changing its prompts or skills.

Skill for Claude CodeCodex

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 skills/entityprocess/agentv/agentv-bench
Any agent
npx skills add EntityProcess/agentv --skill agentv-bench
Clone the repo
git clone --depth 1 https://github.com/EntityProcess/agentv

Made for: Claude Code, Codex.

Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,806 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 $0.00101 $0.05806
Opus 5 $0.00051 $0.02903
Sonnet 5 $0.00020 $0.01161
Haiku 4.5 $0.00010 $0.00581

Measured yesterday against content hash 7527ae09a209, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentv-bench 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.

skills-data/agentv-bench/SKILL.md · 465 lines

How it starts

The opening of the file, as written. The whole thing — 465 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AgentV Bench

A skill for evaluating agents and iteratively improving them through data-driven optimization.

At a high level, the process goes like this:

  • Understand what the agent does and what "good" looks like
  • Write evaluation test cases (EVAL.yaml or evals.json)
  • Run the agent on those test cases, grade the outputs
  • Analyze the results — what's working, what's failing, and why
  • Improve the agent's prompts/skills/config based on the analysis
  • Repeat until you're satisfied

Your job when using this skill is to figure out where the user is in this process and then jump in and help them progress. Maybe they want to start from scratch — help them write evals, run them, and iterate. Maybe they already have results — jump straight to analysis and improvement.

Be flexible. If the user says "I don't need a full benchmark, just help me debug this failure", do that instead.

After the agent is working well, you can also run description optimization to improve skill triggering accuracy (see references/description-optimization.md).

Communicating with the user

This skill is used by people across a wide range of familiarity with evaluation tooling. Pay attention to context cues:

  • "evaluation" and "benchmark" are borderline but OK in most cases
  • For "YAML", "grader", "assertion", "deterministic judge" — see serious cues from the user that they know what those mean before using them without explanation
  • Briefly explain terms if in doubt

When presenting results, default to summary tables. Offer detail on request. In CI/headless mode, skip interactive prompts and exit with status codes.


Step 1: Understand the Agent

Before running or optimizing, understand what you're working with.

  1. Read the agent's artifacts — prompts, skills, configs, recent changes. Understand the full picture: what tools are available, what the expected input/output looks like, what constraints exist.

  2. Identify success criteria — what does "good" look like for this agent? What are the edge cases? What would a failure look like? Talk to the user if this isn't clear from the artifacts alone.

Read the full file on GitHub · 465 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 · 465 lines · 101 tokens per session scan A 7527ae09a209

Subscribe to this mod's changes

agentv-bench is a skill published in the GitHub repository EntityProcess/agentv (15 stars, last pushed 1mo ago), licensed MIT. It adds 101 tokens to every session and 5,806 once invoked, about $0.0005 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 skills, from other repositories

neuron-test-engineer

Write tests for Neuron AI agents, RAG systems, workflows, and tools using the built-in testing utilities. Use this skill when the user mentions testing agents, writing unit tests, mocking AI providers, testing tool execution, verifying RAG retrieval, testing workflow behavior, or creating test cases for Neuron AI…

neuron-core/neuron-ai · 94 tokens

neuron-tool-creator

Create custom tools, toolkits, and MCP integrations for Neuron AI agents. Use this skill when the user mentions creating tools, building toolkits, extending Tool class, defining tool properties, implementing tool execution, MCP server integration, Model Context Protocol, connecting external tools, or tool guidelines.…

neuron-core/neuron-ai · 100 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

neuron-structured-output

Design and implement structured output classes for Neuron AI agents using SchemaProperty attributes and validation rules. Use this skill when the user mentions structured output, JSON schema extraction, data validation, output classes, DTOs for AI responses, extracting structured data from LLM, or configuring property…

neuron-core/neuron-ai · 104 tokens

neuron-workflow-architect

Build custom Neuron AI workflows with nodes, events, middleware, and human-in-the-loop patterns. Use this skill whenever the user mentions workflows, orchestration, event-driven systems, custom agents, complex multi-step processes, human-in-the-loop patterns, or wants to build a custom agentic system from scratch.…

neuron-core/neuron-ai · 89 tokens

neuron-agent-builder

Create and configure Neuron AI agents with providers, tools, instructions, and memory. Use this skill whenever the user mentions building agents, creating AI assistants, setting up LLM-powered chat bots, configuring chat agents, or wants to create an agent that can talk, use tools, or handle conversations. Also…

neuron-core/neuron-ai · 89 tokens