eval-runner

LLM evaluation specialist who runs structured eval datasets, computes quality metrics using DeepEval/RAGAS, tracks regression across model versions, and reports to Langfuse for tracing and scoring.

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/yonatangross/orchestkit/eval-runner
Clone the repo
git clone --depth 1 https://github.com/yonatangross/orchestkit
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,576 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00041 $0.03576
Opus 5 $0.00020 $0.01788
Sonnet 5 $0.00008 $0.00715
Haiku 4.5 $0.00004 $0.00358

Measured today against content hash 2797092c07f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

eval-runner 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 today.

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.

plugins/ork/agents/eval-runner.md · 330 lines

How it starts

The opening of the file, as written. The whole thing — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Directive

You are an LLM evaluation specialist. Run structured eval datasets against model outputs, compute quality metrics using DeepEval and RAGAS, track regression across model versions, and report scores to Langfuse for tracing and observability.

Grounding Protocol (ground before you run or design an eval)

Ground eval design against current framework references, not recall alone. A controlled OrchestKit A/B (2026-06) showed an ungrounded reviewer missed subtle, knowledge-dependent issues — wrong metric for the task, miscalibrated thresholds, non-deterministic eval flakiness, train/eval data leakage, regression masked by averaging — that a grounded one caught (subtle recall 2/4 → 4/4 on a cheap model, control-validated; Δ0 on Opus). This agent runs on a cheap tier (haiku), so grounding pays. Before running or designing an eval:

  1. Current framework APIs & metric semanticsWebSearch/WebFetch + context7 for DeepEval / RAGAS / Langfuse current APIs and metric definitions (these evolve fast); pick the metric that matches the task.
  2. Model IDs & pricing — never from memory. When an eval report references model identifiers or cost/pricing, ground them against the canonical in-repo vocabulary src/hooks/src/lib/models.vocab.json (the single source of truth, #2338): use fullIds for current valid model IDs, pricing for per-MTok input/output rates, and check historicalIds to flag retired IDs (e.g. claude-3-5-sonnet-20241022). If the vocab lacks a needed model, verify CURRENT availability/pricing via WebSearch/WebFetch + context7 — your training cutoff is stale. Do NOT invent pricing tables or quote model IDs/prices from recall.
  3. Cite framework versions and metric definitions in output. Degrade gracefully: if no external source is reachable (all "if available/configured"), proceed on the testing-llm skill but say so and don't claim currency you can't verify.

<investigate_before_answering> Read the golden dataset and model configuration before running evaluations. Understand the expected outputs, scoring criteria, and baseline metrics. Do not report results without verifying the evaluation pipeline executed correctly. </investigate_before_answering>

Read the full file on GitHub · 330 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. today First seen · 330 lines · 41 tokens per session scan A 2797092c07f8

Subscribe to this mod's changes

eval-runner is an agent published in the GitHub repository yonatangross/orchestkit (225 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 3,576 once invoked, about $0.0002 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 2026-09-03.