plugin-testing

A workflow for behaviorally checking Claude Code plugins, including their trigger behavior and the work they carry out. It distinguishes paid model evaluations from ordinary tests for deterministic code.

In plain words
What is it for?
Use it to create evaluation cases, run plugin evaluations, validate plugin structure, investigate failed runs, and write findings.
Why use it?
It helps determine whether a plugin actually behaves as intended instead of checking only its files or manifest.

Skill for Claude CodeCodex

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/spumer/i-m-senior-developer/plugin-testing
Any agent
npx skills add spumer/i-m-senior-developer --skill plugin-testing
Clone the repo
git clone --depth 1 https://github.com/spumer/i-m-senior-developer

Made for: Claude Code, Codex.

Per session 163 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,554 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00163 $0.01554
Opus 5 $0.00081 $0.00777
Sonnet 5 $0.00033 $0.00311
Haiku 4.5 $0.00016 $0.00155

Measured 2d ago against content hash e211abe86ffe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plugin-testing 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 2d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/check_eval_suite.py, scripts/test_check_eval_suite.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.

plugins/plugin-testing/skills/plugin-testing/SKILL.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Проверка поведения плагинов Claude Code

Скилл ведёт работу с проверками плагинов: от выбора вида проверки до разбора красного прогона и записи отчёта. Опирается на измеренные факты, а не на предположения о поведении модели.

Что выбрать: структура или поведение

Сначала определить вид проверки, иначе усилия уйдут не туда.

Вопрос Инструмент Стоимость
Плагин загрузится, манифест и frontmatter валидны? claude plugin validate --strict бесплатно
Скилл срабатывает и ведёт работу правильно? claude plugin eval платно
Детерминированная функция даёт нужный результат? обычный тест рядом с исходником бесплатно

Не писать eval для того, что проверяет обычный тест. Eval нужен только там, где результат существует лишь в поведении модели.

Полный набор вызовов структурной проверки и её измеренные границы — references/validate.md.

Шаг 0. Предусловия

До любого платного прогона убедиться в двух вещах.

Гейт раннего доступа открыт. Проверять в пустом каталоге:

tmpdir=$(mktemp -d)
(cd "$tmpdir" && claude plugin eval)

No eval cases found — открыт, currently in early access — закрыт. Природа гейта и его включение — references/early-access.md.

Версия CLI закреплена. Обновление меняет и формат результата, и поведение модели. Порядок закрепления версии в непрерывной сборке — references/validate.md.

Шаг 1. Сформулировать наблюдаемый договор

Для каждого кейса ответить на четыре вопроса:

  1. какой вход даёт человек;
  2. какое поведение обязательно наступает;
  3. что из этого наблюдаемо снаружи — вызов инструмента, файл, финальный ответ;
  4. какая ошибочная реализация обязана уронить проверку.

Без конкретных ответов кейс не обоснован.

Шаг 2. Собрать кейс

Кейс — каталог под evals/ плагина: prompt.md с параметрами запуска и graders/*.md с критериями. Формат, шесть типов критериев и их ловушки — references/graders.md.

Предпочитать детерминированные критерии. Модель-судью брать только для смысла ответа.

Read the full file on GitHub · 139 lines

Files

What ships with it

9 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. 2d ago First seen · 139 lines · 163 tokens per session scan A e211abe86ffe

Subscribe to this mod's changes

plugin-testing is a skill published in the GitHub repository spumer/i-m-senior-developer (11 stars, last pushed 10d ago), licensed MIT. It adds 163 tokens to every session and 1,554 once invoked, about $0.0008 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens