agent-eval-harness: Instructions file for Claude Code

CLAUDE.md

agent-eval-harness CLAUDE.md is an instructions file for Claude Code, Codex from opendatahub-io/agent-eval-harness. It costs 5,132 tokens per session, scanned A, original, Apache-2.0.

Instructions for a framework that tests AI-agent skills and direct prompts, using MLflow to record runs, evaluations, datasets, and reports.

In plain words
What is it for?
Use them to configure evaluation cases, batch runs, skill tests, prompt tests, scoring, and result tracing.
Why use it?
They clarify whether tests run one case at a time or in a batch, and whether they execute a skill or a plain prompt.

Instructions file for Claude CodeCodex

Written for Claude Code and Codex: ${CLAUDE_SKILL_DIR} variable, but also runs codex exec. Also seen: mentions CLAUDE.md; mentions subagents; names the AskUserQuestion tool.

This is opendatahub-io/agent-eval-harness's own configuration. It tells Claude Code and Codex how to work on agent-eval-harness itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agent-eval-harness configures →

Reuse

Borrowing it

Nothing to install: this file belongs to opendatahub-io/agent-eval-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/opendatahub-io/agent-eval-harness/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/opendatahub-io/agent-eval-harness

Made for: Claude Code, Codex.

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 agent-eval-harness CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/opendatahub-io/agent-eval-harness/claude-md/github.svg)](https://agentmods.dev/instructions/opendatahub-io/agent-eval-harness/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/opendatahub-io/agent-eval-harness/claude-md"><img src="https://agentmods.dev/badge/instructions/opendatahub-io/agent-eval-harness/claude-md/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 agent-eval-harness CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/opendatahub-io/agent-eval-harness/claude-md"><img src="https://agentmods.dev/badge/instructions/opendatahub-io/agent-eval-harness/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5,132 This file is loaded in full into every session.
When invoked 5,132 The same file — it is already loaded in full.
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 $0.05132 $0.05132
Opus 5 $0.02566 $0.02566
Sonnet 5 $0.01026 $0.01026
Haiku 4.5 $0.00513 $0.00513

Measured 5d ago against content hash 02e18996f570, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

agent-eval-harness CLAUDE.md 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 5d 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.

CLAUDE.md · 329 lines

How it starts

The opening of the file, as written. The whole thing — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Eval Harness

Generic evaluation framework for Claude Code skills and agent capabilities. Uses MLflow as the backbone for tracing, evaluation, datasets, and reporting.

Project Status

Phase 1 (core framework), Phase 2 (scoring integration), and Phase 3 (prompt-based evaluation) are implemented. See eval/plans/agent-eval-harness-design.md in the rfe-creator project for the full design doc.

Execution Model

The harness separates how many invocations (execution.mode) from what to execute (execution.skill or execution.prompt):

Execution Mode (case vs batch)

  • case: One invocation per test case (default). The harness loops over cases.
  • batch: One invocation for all cases via batch.yaml. The skill/agent loops internally.

What to Execute (skill vs prompt)

  • Skill mode (execution.skill): Test predefined skill implementations (/my-skill --args). Evaluates skill correctness, quality, and cost efficiency.
  • Prompt mode (execution.prompt): Test agent capabilities directly by sending prompts without a skill wrapper.

Common Patterns

Skill evaluation (case mode):

execution:
  mode: case
  skill: rfe.create
  arguments: '--priority {{ input.priority }} "{{ input.prompt }}"'

Skill evaluation (batch mode):

execution:
  mode: batch
  skill: rfe.speedrun
  arguments: '--input batch.yaml --headless'

Agentic documentation testing (prompt mode) ✨:

execution:
  mode: case
  prompt: "{{ input.prompt }}"

Implemented flavor - Agentic Documentation Testing (see examples/openshift-agentic-docs.md):

  • Documentation effectiveness: Can agents navigate and use your docs?
  • Pattern understanding: Can agents identify and apply code patterns?
  • Constraint compliance: Do agents respect documented rules?
  • API usage: Can agents call APIs with the right fields and structure from documentation alone?

Includes builtin documentation generation prompts (navigation, anti-pattern, authoring, component-usage, architecture) for structured evaluation. See agent_eval/prompts/docs/.

Read the full file on GitHub · 329 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. 5d ago Changed · -1 lines · +50 tokens per session 02e18996f570
  2. 9d ago First seen · 330 lines · 5,082 tokens per session scan A 2884b3ee3738

Subscribe to this mod's changes

agent-eval-harness CLAUDE.md is an instructions file published in the GitHub repository opendatahub-io/agent-eval-harness (40 stars, last pushed 7d ago), licensed Apache-2.0. It adds 5,132 tokens to every session, about $0.0257 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 instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens