orq-run-experiment

orq-run-experiment is a skill for Claude Code from orq-ai/assistant-plugins. It costs 79 tokens per session (4,552 once invoked), scanned A, original, MIT.

A workflow for creating and running experiments in orq.ai, a platform for evaluating AI systems. It compares configurations against a dataset, uses evaluators to check specific failure types, analyses results, and proposes improvements.

In plain words
What is it for?
Evaluating language-model agents and retrieval-augmented generation pipelines, comparing changes, analysing failures, and producing a prioritised improvement plan.
Why use it?
It replaces guesswork with repeatable tests of an AI agent, deployment, conversation flow, or retrieval system. Its rules also require testing prompts and defining concrete pass-or-fail criteria.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool; positional $N argument.

Part of the orq plugin — 17 skills, 6 commands, 1 agent shipped together

Good fit Evaluating language-model agents and retrieval-augmented generation pipelines, comparing changes, analysing failures, and producing a prioritised improvement plan.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/orq-ai/assistant-plugins/orq-run-experiment
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 orq-ai/assistant-plugins --skill orq-run-experiment
Clone the repo
git clone --depth 1 https://github.com/orq-ai/assistant-plugins

Made for: Claude Code.

Or install orq, the plugin that ships this one along with the rest of its 17 skills, 6 commands, 1 agent.

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 orq-run-experiment

README.md
[![agentmods](https://agentmods.dev/badge/skills/orq-ai/assistant-plugins/orq-run-experiment/github.svg)](https://agentmods.dev/skills/orq-ai/assistant-plugins/orq-run-experiment)
Your own site
<a href="https://agentmods.dev/skills/orq-ai/assistant-plugins/orq-run-experiment"><img src="https://agentmods.dev/badge/skills/orq-ai/assistant-plugins/orq-run-experiment/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 orq-run-experiment

Your own site · 80×15
<a href="https://agentmods.dev/skills/orq-ai/assistant-plugins/orq-run-experiment"><img src="https://agentmods.dev/badge/skills/orq-ai/assistant-plugins/orq-run-experiment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,552 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00079 $0.04552
Opus 5 $0.00039 $0.02276
Sonnet 5 $0.00016 $0.00910
Haiku 4.5 $0.00008 $0.00455

Measured 5d ago against content hash 44c7363cc05f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

orq-run-experiment 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.

skills/orq-run-experiment/SKILL.md · 386 lines

How it starts

The opening of the file, as written. The whole thing — 386 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run Experiment

allowed-tools here is a curated read/search allowlist so lookups run without permission prompts; create_*/update_*/delete_*/invoke_* and shell commands are intentionally not pre-approved and still prompt. The delete_* tools are disabled entirely while this skill is active.

You are an orq.ai evaluation engineer. Your job is to design, execute, and analyze experiments that measure LLM pipeline quality — then turn results into prioritized, actionable improvements.

Constraints

  • NEVER run an experiment without a structured dataset. Check if a suitable one exists first; create one if not.
  • NEVER use generic "helpfulness" or "quality" evaluators. Build criteria from error analysis.
  • NEVER bundle 5+ criteria into one evaluator. One evaluator per failure mode.
  • NEVER re-run an experiment without making a specific, documented change first.
  • NEVER jump to a model upgrade before trying prompt fixes, few-shot examples, and task decomposition.
  • ALWAYS fix the prompt before building an evaluator — many "failures" are underspecified instructions.
  • ALWAYS use Binary Pass/Fail per criterion, not Likert scales.
  • A 100% pass rate means your eval is too easy, not that your system is perfect — target 70-85%.

Why these constraints: Evaluators that bundle criteria produce uninterpretable scores. Generic evaluators miss application-specific failure modes. Re-running without changes wastes budget and creates false confidence.

Companion Skills

  • orq-build-agent — create and configure orq.ai agents
  • orq-build-evaluator — design judge prompts for subjective criteria
  • orq-analyze-traces — build failure taxonomies from production traces
  • orq-generate-synthetic-dataset — generate diverse test scenarios
  • orq-improve-agent — analyze and rewrite prompts using a structured guidelines framework
  • orq-cli — the same platform operations from a shell, for anything that must run again without an agent present (CI, cron, scripts, bulk): auth via ORQ_API_KEY, --json output. See its "MCP tools or the CLI?" table before choosing.

Read the full file on GitHub · 386 lines

Files

What ships with it

5 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. 5d ago Changed · -6 lines 44c7363cc05f
  2. 9d ago First seen · 392 lines · 79 tokens per session scan A 6a6f408c1494

Subscribe to this mod's changes

orq-run-experiment is a skill published in the GitHub repository orq-ai/assistant-plugins (6 stars, last pushed 8d ago), licensed MIT. It adds 79 tokens to every session and 4,552 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 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

jetson-validate-image

Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.

NVIDIA/skills · 50 tokens

atmos-validation

Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.

cloudposse/atmos · 31 tokens

skill-benchmark

Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.

HoangNguyen0403/agent-skills-standard · 16 tokens