A skill for writing, running, and repairing human-written acceptance checks stored in an `acceptance/ACCEPTANCE.md` file. Acceptance checks are executable tests of whether the finished result matches the requested outcome.

Use it to author checks, run them, and repair code when checks fail.

It gives the project a repeatable way to check expected results and identify code that fails those checks, while making clear that passing checks is not a guarantee.

acceptance — Skill for Claude Code by cryndoc: A skill for writing, running, and repairing human-written acceptance…

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/cryndoc/polisade-orchestrator/acceptance

Any agent

npx skills add cryndoc/polisade-orchestrator --skill acceptance

Clone the repo

git clone --depth 1 https://github.com/cryndoc/polisade-orchestrator

Made for: Claude Code.

Or install polisade, the plugin that ships this one along with the rest of its 26 skills, 2 commands.

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/cryndoc/polisade-orchestrator/acceptance.svg)](https://agentmods.dev/skills/cryndoc/polisade-orchestrator/acceptance)

Your own site

<a href="https://agentmods.dev/skills/cryndoc/polisade-orchestrator/acceptance"><img src="https://agentmods.dev/badge/skills/cryndoc/polisade-orchestrator/acceptance.svg" alt="Measured on agentmods" 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 5,006 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.

Model	Per session	Once invoked
Fable 5.1	$0.00129	$0.05006
Opus 5	$0.00064	$0.02503
Sonnet 5	$0.00026	$0.01001
Haiku 4.5	$0.00013	$0.00501

Measured 6d ago against content hash 3b457469d44e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

acceptance 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 6d 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.

skills/acceptance/SKILL.md · 363 lines

How it starts

The opening of the file, as written. The whole thing — 363 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/polisade:acceptance [author | run | repair] — Приёмка как практика

Человек записывает образ результата — пары «одна фраза интента + один исполняемый чек» — в acceptance/ACCEPTANCE.md. Скилл гоняет эти чеки и чинит код по красным. Разбор файла, линт и прогон — детерминированные (scripts/polisade_acceptance.py, stdlib-only); интервью и ремонт — работа модели.

⚠️ ЧЕСТНАЯ РАМКА — прочитай и повтори пользователю при первом запуске

┌─────────────────────────────────────────────────────────────┐
│  Это приёмка-ПРАКТИКА (best-effort), а НЕ приёмка-ГАРАНТИЯ. │
│                                                             │
│  Файл проверок лежит в репозитории: он виден модели и       │
│  доступен ей на запись. Запрет «не правь проверки, чини     │
│  код» держится ПРОМПТОМ этого скилла, а не барьером.        │
│  Прогон умеет ЗАМЕТИТЬ подмену (дайджесты пар и их          │
│  приборов), но не                                           │
│  умеет её ПРЕДОТВРАТИТЬ.                                    │
└─────────────────────────────────────────────────────────────┘

Что это значит на практике:

зелёная приёмка здесь = «чеки прошли», а не «результат гарантирован»;
самый вероятный способ получить ложную зелень — ослабить сам чек; ровно этот путь и не закрывается промптом;
приёмка с гарантией (оракул вне досягаемости исполнителя, независимый судья, барьеры против правки тестов) — свойство отдельного платного продукта; граница описана в документе docs/what-works-without-paid-parts.md репозитория Polisade Orchestrator (в поставку плагина docs/ не входит).

⛔ Запрещено (класс F1 — «отказ способности подан как положительный факт»): подавать вывод этого скилла как «приёмка пройдена, качество подтверждено». Пиши как есть: «чеки приёмки зелёные (best-effort, проверки правились/не правились — см. отчёт)».

Использование

/polisade:acceptance author            # интервью: записать образ результата (пары)
/polisade:acceptance author AC-003     # добавить/переписать ОДНУ пару
/polisade:acceptance run               # прогнать все чеки, показать красные
/polisade:acceptance run AC-001        # прогнать одну пару
/polisade:acceptance repair            # пересдача: чинить КОД по красным чекам
/polisade:acceptance repair AC-002     # пересдача по одной паре

Read the full file on GitHub · 363 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.

6d ago First seen · 363 lines · 129 tokens per session scan A 3b457469d44e

Subscribe to this mod's changes

acceptance is a skill published in the GitHub repository cryndoc/polisade-orchestrator (7 stars, last pushed 11d ago), licensed Apache-2.0. It adds 129 tokens to every session and 5,006 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 2026-08-31.

Autonomous Agents E2E testing LLM Testing ai-agents claude-code claude-code-plugin developer-tools

tdd-workflow

Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.

affaan-m/ECC · 43 tokens

e2e-testing

Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies. Use when writing Playwright tests, structuring page objects, or fixing flaky E2E runs in CI.

affaan-m/ECC · 53 tokens

browser-check

Drive a real browser and come back with a MEASUREMENT rather than an impression - console errors and >=400 responses as counts, computed styles as JSON when appearance is disputed. Use when work touches UI, when a review must verify one, or when fidelity-gate asks for its measurement.

jjanczur/tyran · 58 tokens

acceptance