evaluating-llms-harness

evaluating-llms-harness is a skill for Claude Code, Codex from ariffazil/AAA. It costs 29 tokens per session (3,517 once invoked), scanned A, original, AGPL-3.0.

A tool for testing language models against more than 60 academic benchmarks, including tests of knowledge, coding, maths, truthfulness, and common-sense reasoning.

In plain words
What is it for?
Use it to run benchmark evaluations with Hugging Face models, vLLM, or model APIs and report the results.
Why use it?
It provides repeatable results for comparing models or checking whether training improves them, instead of relying on separate manual tests.

Skill for Claude CodeCodex

Which agent this was written for is unclear — body not stored (licence); the path alone says nothing.

Good fit Use it to run benchmark evaluations with Hugging Face models, vLLM, or…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ariffazil/aaa/lm-evaluation-harness
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.

Any agent
npx skills add ariffazil/AAA --skill lm-evaluation-harness
Clone the repo
git clone --depth 1 https://github.com/ariffazil/AAA

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 evaluating-llms-harness

README.md
[![agentmods](https://agentmods.dev/badge/skills/ariffazil/aaa/lm-evaluation-harness.svg)](https://agentmods.dev/skills/ariffazil/aaa/lm-evaluation-harness)
Your own site
<a href="https://agentmods.dev/skills/ariffazil/aaa/lm-evaluation-harness"><img src="https://agentmods.dev/badge/skills/ariffazil/aaa/lm-evaluation-harness.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,517 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown 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 $0.00029 $0.03517
Opus 5 $0.00015 $0.01758
Sonnet 5 $0.00006 $0.00703
Haiku 4.5 $0.00003 $0.00352

Measured 6d ago against content hash 5426016d51e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

evaluating-llms-harness scanned grade A with 1 finding 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 6d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

os.system(f"./eval_checkpoint.sh checkpoints step-{step}")
.hermes-archived-2026-08-15/skills/mlops/evaluation/lm-evaluation-harness/SKILL.md · 499 lines

The source is not reproduced here

Licensed AGPL-3.0

The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 499 lines · 29 tokens per session scan A 5426016d51e3

Subscribe to this mod's changes

evaluating-llms-harness is a skill published in the GitHub repository ariffazil/AAA (2 stars, last pushed 2d ago), licensed AGPL-3.0. It adds 29 tokens to every session and 3,517 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

prompt-cache-agent-harness

Plan and inspect prompt-cache behavior for long-running Claude agent loops. Use when a user wants to split stable tool, system, and history context into cacheable layers, compare captured cache metadata, estimate cost impact from supplied pricing inputs, or keep durable memory outside the cached prefix.

Prompthon-IO/agent-systems-handbook · 61 tokens

vertex-ai

Build and deploy ML models and generative AI workloads — models, prompts, tuning and endpoints — on Vertex AI. Covers Model Garden, the Gemini API, custom training, endpoint deployment, and IAM. Warns before deploying endpoints (billable). Integrates with Vertex AI MCP server. Use when the user mentions: Gemini on…

jpantsjoha/googlecloud-plugin · 136 tokens

arif-a2a-call

A2A v1.0.0 client + 888 JUDGMENT integration for OPENCLAW. Use when candidate actions require ASI deliberation or A2A federation with APEX (formerly Hermes).

ariffazil/arifOS · 51 tokens

VISION_ORGAN

Shadow-mode vision intelligence pipeline for the arifOS federation. Generates image candidates via MiniMax, analyzes via Qwen Token Plan, scores via atomic quality gates.

ariffazil/arifOS · 0 tokens

agent-v3-memory-specialist

Agent skill for v3-memory-specialist - invoke with $agent-v3-memory-specialist.

ruvnet/ruflo · 25 tokens

neural-training

Neural pattern training with SONA (Self-Optimizing Neural Architecture), MoE (Mixture of Experts), and EWC++ for knowledge consolidation. Use when: pattern learning, model optimization, knowledge transfer, adaptive routing. Skip when: simple tasks, no learning required, one-off operations.

ruvnet/ruflo · 64 tokens