opik-annotate

opik-annotate is a skill for Claude Code from comet-ml/opik-mcp. It costs 162 tokens per session (2,584 once invoked), scanned A, original, Apache-2.0.

A tool for creating a human review queue in Opik, an observability platform for checking an AI system's traces or conversations. It saves a custom HTML view so reviewers see useful content instead of raw JSON.

In plain words
What is it for?
Use it to create or change an Opik annotation queue, choose whether it covers individual traces or whole threads, and define what reviewers should inspect. The work changes Opik review settings, not application code.
Why use it?
It makes review items easier for people to judge, such as showing an email beside a reply or a conversation as chat bubbles. It also bases the view on real recorded data rather than guessed fields.

Skill for Claude Code

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

Part of the opik plugin — 11 skills, 1 MCP server shipped together

Good fit Use it to create or change an Opik annotation queue, choose whether it covers individual traces or whole threads, and define what reviewers should inspect. The work changes Opik review settings, not application code.

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

Made for: Claude Code.

Or install opik, the plugin that ships this one along with the rest of its 11 skills, 1 MCP server.

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-annotate

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/comet-ml/opik-mcp/opik-annotate"><img src="https://agentmods.dev/badge/skills/comet-ml/opik-mcp/opik-annotate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 162 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,584 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 $0.00162 $0.02584
Opus 5.5 $0.00065 $0.01034
Sonnet 5.5 $0.00032 $0.00517
Haiku 4.5 $0.00016 $0.00258

Measured 16d ago against content hash d07d96adae12, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

opik-annotate 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 16d 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.

plugins/opik/skills/opik-annotate/SKILL.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Annotate — A Review Queue Annotators Can Read

Definition of done: the queue exists with the view saved, and the user knows where to check it — the write returned without a warning, and the answer carries the queue's link. A view is built from the project's real traces or threads, never from a guessed shape. If the queue or the view can't be saved, stop at the first genuine blocker and return exactly one next step.

Operate: look at real items first, cover every shape you saw, show text not JSON, keep scoring in Opik's own panel. This skill writes to Opik only and changes no application code.

Inputs

/opik-annotate <what annotators judge> ("the drafted reply", "whether the agent solved the ticket"), /opik-annotate <queue name or id> (change that queue's view), or a request to remove a view. Infer the rest; optional overrides: project (default: configured) · scope (default: trace; thread for whole conversations) · feedback definitions (default: the queue's own).

Activation — the only in-scope work

1. Resolve the project and the queue

With the Opik MCP connected: list('annotation_queue', project_name=…) shows the project's queues with their scope and item count; read('annotation_queue', id_or_name) returns one with its instructions, feedback definitions and view summary. The view's html is stated by size; read('annotation_queue', id, fields=['annotator_view.html']) returns it whole — read it before changing a view, and change only what was asked.

2. Look at real items before writing anything

  • Queue with items: list('trace', project_name=…, filters='annotation_queue_ids contains "<queue_id>"', size=20) (list('thread', …) for a thread queue), then read('trace', id) on two or three that differ.
  • Empty or new queue: the project's latest traces or threads instead, and say so ("the queue has no items yet, so the view is built from the latest traces").

Note every shape input, output and metadata take: objects, arrays, or strings that hold JSON. A view that handles only the most common shape fails annotators on the rest.

Read the full file on GitHub · 126 lines

Files

What ships with it

1 file 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. 16d ago First seen · 126 lines · 162 tokens per session scan A d07d96adae12

Subscribe to this mod's changes

opik-annotate is a skill published in the GitHub repository comet-ml/opik-mcp (226 stars, last pushed today), licensed Apache-2.0. It adds 162 tokens to every session and 2,584 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-10-29.

Related

opik-annotate compared with skills from other repositories

opik-annotate next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
opik-annotatecomet-ml/opik-mcpSkill226todayApache-2.0A162Claude Code
cortex-explore-memorycdeust/CortexSkill77todayMITA91Claude Code
qmclaw-workbenchxi-zhao/OpenQuantumSkill723d agoMITA124Codex
quantum-groverxi-zhao/OpenQuantumSkill723d agoMITA62Claude Code, Codex
quantum-algorithmsxi-zhao/OpenQuantumSkill723d agoMITA34Claude Code, Codex
alicebob-cat-circuitsxi-zhao/OpenQuantumSkill723d agoMITA51Claude Code, Codex
guppy-programsxi-zhao/OpenQuantumSkill723d agoMITA48Claude Code, Codex