Opik is an open-source platform for tracing, evaluating, and monitoring applications that use large language models, retrieval systems, or AI agents. Teams use it to inspect agent activity, manage prompts, run evaluations, and monitor these applications in production.
Borrowing it
Nothing to install: this file belongs to comet-ml/opik. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/comet-ml/opik/main/.agents/skills/writing-visual-tests/SKILL.mdgit clone --depth 1 https://github.com/comet-ml/opikWrote 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.
[](https://agentmods.dev/skills/comet-ml/opik/writing-visual-tests)<a href="https://agentmods.dev/skills/comet-ml/opik/writing-visual-tests"><img src="https://agentmods.dev/badge/skills/comet-ml/opik/writing-visual-tests/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.
<a href="https://agentmods.dev/skills/comet-ml/opik/writing-visual-tests"><img src="https://agentmods.dev/badge/skills/comet-ml/opik/writing-visual-tests.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 8 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 161 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Rogue Agent · line 133 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 134 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium MCP Rug Pull · line 167 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 200 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 202 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 207 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 211 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00108 | $0.07979 |
| Opus 5.5 | $0.00043 | $0.03192 |
| Sonnet 5.5 | $0.00022 | $0.01596 |
| Haiku 4.5 | $0.00011 | $0.00798 |
Grade C, and why
writing-visual-tests scanned grade C with 2 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 2mo 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
| `test-results/` | Playwright's per-test output (failure screenshots, videos, traces) | Regenerated every run — safe to delete: `rm -rf test-results`. | Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://localhost:5555/health How it starts
The opening of the file, as written. The whole thing — 350 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Visual Tests
This skill adds a screenshot-comparison test to Opik's visual regression suite. Unlike the functional E2E suite (tests_end_to_end/e2e/, see writing-e2e-tests), this suite's assertion is the screenshot — so seeding must produce deterministic pixels, not just correct data.
Announce at start: "I'm using the writing-visual-tests skill to add a visual test for X."
Plan before implementing. Before writing or editing any file, work through step 1 ("Scope") of "The loop" below and present the user a short plan: which page/panel and states you'll cover, what new seed route/client method (if any) you'll add, which spec file and project the new test(s) will live in (and why, per "One project per screenshot group"), and the resulting screenshot name(s). Wait for the user's explicit approval before starting step 2 (seeding) or any other implementation work. Only skip this pause if the user's request already specifies all of these choices unambiguously.
Where tests live
The suite is at tests_end_to_end/visual-tests/:
- Specs:
tests/<area>.spec.ts— e.g.visual-comparison.spec.ts(happy-path pages),empty-states.spec.ts,trace-sidebar.spec.ts. Onetest.describeper spec, onetest.beforeAllthat seeds data and resolves the project ID. - Page objects:
page-objects/<page>.page.ts— see "Page object pattern" below; always follow it, don't freehand a different shape. - Seeding:
helpers/test-helper-client.ts— a typed HTTP client over the Flasktest-helper-service(../test-helper-service/routes/*.py), which wraps the real Python SDK. Add a new route + a new client method together; never seed by clicking through the UI. - Screenshot util:
tests/utils/screenshot.ts—screenshot(page, name, extraMasks?). Read this whole file before writing a new spec. - Global setup/teardown:
global-setup.ts/global-teardown.ts— create/delete the fixed-name projects (visual-project,visual-empty-project,visual-sidebar-project, …) used across specs. Fixed names, no timestamp suffix, so screenshots are identical across runs. Give each new portion of screenshots its own project — see "One project per screenshot group" below. - Baselines:
screenshots/baseline/*.png— see "Baselines are local and gitignored" below before you assume one exists.
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.
- 2mo ago First seen · 350 lines · 108 tokens per session scan C ac63c2458fdb
writing-visual-tests is a skill published in the GitHub repository comet-ml/opik (22,998 stars, last pushed today), licensed Apache-2.0. It adds 108 tokens to every session and 7,979 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
langbot-testing
Test LangBot WebUI and core product flows with an automated browser and backend logs. Use when validating the configured LangBot frontend, pipeline Debug Chat, model provider setup and test buttons, bot and knowledge-base UI flows, or troubleshooting failed LangBot end-to-end tests.
mailagent
Temporary inboxes for agent signup QA — create disposable addresses, wait for verification email, extract OTP or magic links. Use when automating signup, login, or email verification without parsing HTML manually.
browser-qa
A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.
api-tester
A tool for creating and checking API tests from the real API contract and implementation. An API is the agreed way that software sends requests and receives responses.
accessibility-testing-expert
Expert guide for automated and manual Web Accessibility (a11y) testing — axe-core, Pa11y, Playwright a11y, screen reader testing, and WCAG 2.2 Level AA/AAA compliance / Panduan ahli pengujian aksesibilitas web.
e2e-testing-expert
Expert guide for End-to-End (E2E) testing with Playwright 1.50+, Clock API, ARIA snapshots, test fixtures, and Vitest 3+ / Panduan ahli pengujian E2E dengan Playwright 1.50+, Clock API, ARIA snapshots, dan Vitest 3+.