opik-test

opik-test is a skill for Claude Code from comet-ml/opik-mcp. It costs 141 tokens per session (2,694 once invoked), scanned A, original, Apache-2.0.

A tool that turns a failed Opik trace into a stored regression test. Opik is a platform for recording and evaluating AI application runs; the test keeps the failing input and simple pass/fail checks.

In plain words
What is it for?
It captures a trace or described failure, creates a test item in an Opik suite, and adds one or two binary assertions for use by the Opik comparison tool. It does not change application code.
Why use it?
It makes an AI failure repeatable instead of relying on a description or a one-off manual check. That lets a later change be tested against the same case.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Claude Code; mentions Codex.

Good fit It captures a trace or described failure, creates a test item in an Opik suite, and adds one or two binary assertions for use by the Opik comparison tool. It does not change application code.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/comet-ml/opik-mcp/opik-test
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 comet-ml/opik-mcp --skill opik-test
Clone the repo
git clone --depth 1 https://github.com/comet-ml/opik-mcp

Made for: Claude Code.

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 opik-test

README.md
[![agentmods](https://agentmods.dev/badge/skills/comet-ml/opik-mcp/opik-test/github.svg)](https://agentmods.dev/skills/comet-ml/opik-mcp/opik-test)
Your own site
<a href="https://agentmods.dev/skills/comet-ml/opik-mcp/opik-test"><img src="https://agentmods.dev/badge/skills/comet-ml/opik-mcp/opik-test/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 opik-test

Your own site · 80×15
<a href="https://agentmods.dev/skills/comet-ml/opik-mcp/opik-test"><img src="https://agentmods.dev/badge/skills/comet-ml/opik-mcp/opik-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 141 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,694 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.
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 $0.00141 $0.02694
Opus 5 $0.00071 $0.01347
Sonnet 5 $0.00028 $0.00539
Haiku 4.5 $0.00014 $0.00269

Measured 3d ago against content hash cc992d100690, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-21, from the pricing page.

Security

Grade A, and why

opik-test 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 3d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (evals/fixtures/toolbug/agent.py, evals/grader.py, evals/metrics.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

src/opik_mcp/skills/opik-test/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test — Capture a Failing Case as a Repeatable Check

Definition of done: one test-suite item exists in Opik that reproduces the failure — its data carries the failing input (and the expected output when one is known), and it has one or two binary assertions that would have failed on the bad trace and pass on a correct one. The item is in a named suite scoped to the project, is confirmed by reading it back, and is ready for /opik-compare to run. If the case can't be captured, stop at the first genuine blocker and return exactly one next step. Writing a pytest file, or describing a test in prose, is not success.

Operate: extract the case from real trace data, write assertions a judge can decide with a yes or no, store them where /opik-compare will find them — and change no application code. This skill writes to Opik, never to the repo.

Inputs

The entry point is /opik-test <trace-id> (capture that trace), /opik-test <describe the failure> (find the trace, or capture from the description alone), or /opik-test right after /opik-explain (capture the trace it just explained). Infer the rest; treat these as optional overrides:

  • suite name (default: <project>-regressions) · project (default: the trace's project, else the configured one) · expected output (default: none — assertions carry the expectation) · execution policy (default: the suite's; runs_per_item: 3, pass_threshold: 2 only for an intermittent failure).

Ask only at a genuine, non-inferable blocker (see Blockers).

Activation — the only in-scope work

1. Resolve the case

  • A trace id (uuid-shaped): that trace is the case.
  • A description ("the refund answer is wrong", "it hallucinated the shipping time"): search_traces on the project for the matching trace (error, low score, or free-text match) and take the best one. If none matches, capture from the description alone — the user's input and expectation become the item.
  • Confirm Opik is reachable: if ~/.opik.config exists or OPIK_API_KEY is set, use it. Otherwise → Blocker ("run opik configure, then rerun").

Read the full file on GitHub · 132 lines

Files

What ships with it

8 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. 3d ago First seen · 132 lines · 141 tokens per session scan A cc992d100690

Subscribe to this mod's changes

opik-test is a skill published in the GitHub repository comet-ml/opik-mcp (221 stars, last pushed 4d ago), licensed Apache-2.0. It adds 141 tokens to every session and 2,694 once invoked, about $0.0007 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 2026-09-18.

Related

Other skills, from other repositories

aba-precision-protocol

FOUNDATIONAL BEHAVIORAL PROTOCOL — ABA-based precision execution rules. Every prompt processed must follow these rules. Mistakes caught late create intermittent reinforcement of wrong patterns. Stop-fix-verify before proceeding.

dcostenco/prism-coder · 48 tokens

Langfuse LLM Observability Testing

Instrument LLM apps with Langfuse tracing, then use traces, scores, and datasets to test in production, run evaluations on real traffic, catch regressions, and close the loop from incident to golden dataset.

PramodDutta/qaskills · 52 tokens

local-rag-search

Efficiently perform web searches using the mcp-local-rag server with semantic similarity ranking. Use this skill when you need to search the web for current information, research topics across multiple sources, or gather context from the internet without using external APIs. This skill teaches effective use of…

nkapila6/mcp-local-rag · 80 tokens

luma-vision

A skill for analyzing images with several external vision models. It is activated only when a user starts a request with /skill luma-vision and includes an image.

JochenYang/luma-mcp · 37 tokens

agent-tests

MUST READ before calling RunAgentTests or touching agent-tier test infrastructure -- these tests spawn real AI clients (Claude Code, Codex) and SPEND SUBSCRIPTION USAGE; never run casually. Tier model, async runner rationale, auth/isolation rules.

dylanroscover/Embody · 56 tokens

blazemeter-api-reference

Comprehensive reference for BlazeMeter REST APIs, including authentication, identifiers, and API endpoints. Use when working with BlazeMeter APIs for (1) Understanding BlazeMeter REST API structure, (2) Authenticating API requests, (3) Obtaining identifiers (Workspace ID, Project ID, Test ID, etc.), (4) Using Test…

Blazemeter/bzm-mcp · 109 tokens