A check that confirms a change actually appears and behaves correctly in a real web page or other visible interface. It treats seeing the result work as part of finishing the task.

Use it after changing a page, user interface, live view, or screen interaction. It verifies the result through a real browser or an automated browser test.

A build, type check, or test can pass while the screen is still broken. This check catches problems that only appear when the application runs and someone views or uses it.

verify — Skill for Claude Code by Marcel-Bich

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add Marcel-Bich/marcel-bich-claude-marketplace

Claude Code

/plugin install credo

Made for: Claude Code.

Or install credo, the plugin that ships this one along with the rest of its 26 skills, 15 commands, 6 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/marcel-bich/marcel-bich-claude-marketplace/verify/github.svg)](https://agentmods.dev/skills/marcel-bich/marcel-bich-claude-marketplace/verify)

Your own site

<a href="https://agentmods.dev/skills/marcel-bich/marcel-bich-claude-marketplace/verify"><img src="https://agentmods.dev/badge/skills/marcel-bich/marcel-bich-claude-marketplace/verify/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/marcel-bich/marcel-bich-claude-marketplace/verify"><img src="https://agentmods.dev/badge/skills/marcel-bich/marcel-bich-claude-marketplace/verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 129 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,659 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.

Model	Per session	Once invoked
Fable 5.1	$0.00129	$0.02659
Opus 5	$0.00064	$0.01329
Sonnet 5	$0.00026	$0.00532
Haiku 4.5	$0.00013	$0.00266

Measured 11d ago against content hash ffa3f3745655, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

verify 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 11d 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/credo/skills/verify/SKILL.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

verify - visual verification as Definition of Done

Visual verification is the credo Definition-of-Done gate for anything with a runtime surface. If a change renders something, updates something on screen, or reacts to a user action, it is not done until that behavior has been observed - either by the user in a real browser, or by a reliable automated Playwright check that drives the real build. This skill is the DoD gate that ui: true items require.

Task backend. If the task backend is gsd (.credo/config: task_backend, or the CREDO_TASK_BACKEND env override), the credo item lifecycle is inactive, so there is no credo item to move to done - GSD owns task tracking. The verification method here still applies as a general "prove it renders" tool; just do not gate a credo item with it in that mode.

What does NOT count as verification

None of these are a substitute for visual proof:

pytest / unit tests / integration tests passing
node --check, a type-check, a lint pass, or a successful build
"the file is served" / "the server returned 200"
a subagent code-review or a static read of the source

They can all be green while the surface renders broken, never updates, or ignores the user. Verification means the rendered surface was exercised and observed.

Two accepted forms of proof

Browser verification by the user - the user opens the real surface and confirms it.
A reliable Playwright check - drives the actual build in a real browser, measures computed layout, exercises the real interaction, and captures evidence.

Anything else is "wired-but-behavior-unverified", not "exercised".

Required test level for done (project-configurable)

Which test level a change must pass before it may move to done is resolved by a fallback chain, so a project can pin its own primary method without credo hardcoding any project-specific tool or device:

Project primary test level. credo ships verify.primary_test pre-filled with a default example (a debug read/write device driving a state machine) so the setting is discoverable instead of silently empty. credo does not know what the stage is; it is referenced only through the config key. Read it with:

Read the full file on GitHub · 222 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.

11d ago First seen · 222 lines · 129 tokens per session scan A ffa3f3745655

Subscribe to this mod's changes

verify is a skill published in the GitHub repository Marcel-Bich/marcel-bich-claude-marketplace (13 stars, last pushed 2d ago), licensed MIT. It adds 129 tokens to every session and 2,659 once invoked, about $0.0006 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 2026-08-30.

Claude Code E2E testing Testing ai-tools anthropic claude claude-ai claude-code-plugins

k8s-sidecar-testing

Test the nat464-sidecar demo topology in a selected Kubernetes test namespace, verify IPv6 translation paths, and compare HTTP latency. Includes optional disposable Multipass/k3s setup.

fakoli/fakoli-plugins · 43 tokens

demo-review

Quality-checks a rendered demo video before it ships — extracts frames, grades each section against its successCriteria, and finds spinners, empty states, clipped text, exposed secrets, audio/video desync, and pacing problems. Use after a draft render, before a final render, or when asked whether a demo video is good…

lukaskellerstein/claude-my-marketplace · 72 tokens

screenshot-automation

Generates an automated App Store screenshot pipeline with UI tests for screenshot capture, device framing, localized caption overlays, and multi-size batch export. Use when user wants automated screenshots, App Store screenshot generation, or a fastlane snapshot replacement.

rshankras/claude-code-apple-skills · 52 tokens

verify