verify

verify is a skill for Claude Code, Codex from andrewcigan/vibe-dev-plugin. It costs 53 tokens per session (1,723 once invoked), scanned A, original, MIT.

A four-layer check for deciding whether a software feature is truly finished: code checks, runtime tests, end-to-end tests, and user-reported confirmation.

In plain words
What is it for?
Use it to check syntax and static analysis, run unit and integration tests, perform end-to-end checks, and confirm reported behavior.
Why use it?
It prevents a feature from being marked done just because one test passes while other parts may still be broken.

Skill for Claude CodeCodex

Part of the vibe-dev plugin — 29 skills, 24 agents, 7 hooks shipped together

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.

agentmods
npx agentmods add skills/andrewcigan/vibe-dev-plugin/verify
Any agent
npx skills add andrewcigan/vibe-dev-plugin --skill verify
Clone the repo
git clone --depth 1 https://github.com/andrewcigan/vibe-dev-plugin

Made for: Claude Code, Codex.

Or install vibe-dev, the plugin that ships this one along with the rest of its 29 skills, 24 agents, 7 hooks.

Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,723 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00053 $0.01723
Opus 5 $0.00026 $0.00861
Sonnet 5 $0.00011 $0.00345
Haiku 4.5 $0.00005 $0.00172

Measured 3d ago against content hash e1f4b8667088, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

verify scanned grade A with 1 finding 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.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

layer_4/5; api → curl + статус; cli → команда + exit; job → лог реального прогона;
skills/verify/SKILL.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/verify

Four-layer verification (4-уровневая проверка) активной фичи.

Layer 0: Enforcement жив? (v6.2 F2)

P="$(cat .harness/profile 2>/dev/null)"; HB=.harness/hooks-heartbeat
case "$P" in pending-*) echo "❌ профиль $P не подтверждён живым хуком"; esac
[ -f "$HB" ] && [ $(( $(date +%s) - $(awk '{print $1;exit}' "$HB") )) -le 1800 ] \
  || echo "❌ heartbeat несвежий — хуки в этой сессии НЕ работают"

❌ → СТОП: verify при мёртвых сторожах легко станет «зелёным враньём» (passing-гейт не проверит evidence). Сначала /doctor.

Layer 1: Syntax & Static Analysis

Минимальный gate, фундамент.

# JavaScript/TypeScript
npm run check          # tsc --noEmit
npm run lint           # eslint

# Python
ruff check .
mypy src/

# Common
git diff --check       # whitespace

Если хоть что-то красное — STOP, чинить.

Layer 2: Runtime Behavior (unit + integration)

# из feature_list.json[active].verification.layer_2_runtime
npm test -- --filter=<feature>
# или
pytest tests/test_<feature>.py -v

Все тесты зелёные = pass.

Layer 3: End-to-End

Закрывает lecture-10 (E2E меняет результат).

# Из feature_list.json[active].verification.layer_3_e2e
./e2e/test-<feature>.sh
# или
playwright test e2e/<feature>.spec.ts
# или chrome-devtools-mcp scenarios

Кейс из реального проекта: unit-тесты прошли 3/3, e2e нашёл 5 дефектов на границах. Этот слой не пропускать.

Evidence по поверхности (v6.2 F5)

Тип доказательства обязан соответствовать surface фичи — полная таблица: rules/verification-lanes.md. Кратко: ui → браузер + layer_4/5; api → curl + статус; cli → команда + exit; job → лог реального прогона; service → behavior-probe (НЕ pgrep). Hook не пустит passing с пустым evidence у этих поверхностей.

«Не могу прогнать живьём» → Live-Target Probe, 4 яруса (см. ту же таблицу): найти живой сервер → поднять самому → preview-деплой → только после задокументированного провала всех трёх — честный UNIT_VERIFIED (не passing). Skip молча — не вариант.

Read the full file on GitHub · 163 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.

  1. 3d ago First seen · 163 lines · 53 tokens per session scan A e1f4b8667088

Subscribe to this mod's changes

verify is a skill published in the GitHub repository andrewcigan/vibe-dev-plugin (5 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 1,723 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

penguin-harness-manual-test

Use when standing PenguinHarness up to try a change by hand — launching the Web App, the desktop shell, the landing page or the docs site to click through it, screenshot it, or reproduce a report. Covers the four dev entry points and their ports, which data root each writes to, and the four ways a healthy setup looks…

Prism-Shadow/penguin-harness · 77 tokens

moai-ref-testing-pyramid

Test pyramid strategy, coverage targets, test patterns, and quality metrics reference. Agent-extending skill that amplifies manager-develop test-creation and quality-validation work with production-grade testing patterns. NOT for: production code implementation, architecture design, DevOps, security audits.

modu-ai/moai-adk · 61 tokens

cherry-pr-test

Test Cherry Studio PRs by resolving and checking out a PR, statically inspecting its changes, running interactive UI tests against a safely tracked Electron instance through CDP, producing a structured report, cleaning up only the owned test instance, and restoring the original branch.

CherryHQ/cherry-studio · 57 tokens

local-test

Build, run, and test IronClaw locally using Docker containers and Chrome MCP browser automation.

suyoumo/ClawProBench · 22 tokens

playwright-pro

Production-grade Playwright testing toolkit. Use when the user mentions Playwright tests, end-to-end testing, browser automation, fixing flaky tests, test migration, CI/CD testing, or test suites. Generate tests, fix flaky failures, migrate from Cypress/Selenium, sync with TestRail, run on BrowserStack. 55 templates…

adriannoes/awesome-agentic-ai · 77 tokens

browserstack

Run tests on BrowserStack. Use when user mentions "browserstack", "cross-browser", "cloud testing", "browser matrix", "test on safari", "test on firefox", or "browser compatibility".

adriannoes/awesome-agentic-ai · 44 tokens