swarm-qa

swarm-qa is a skill for Claude Code from smk-labs/claude-plugins. It costs 140 tokens per session (1,104 once invoked), scanned C, original, MIT.

A four-phase quality-assurance workflow for a live product: a broad code audit, deep live testing, coordinated fixes, and final verification. It uses multiple agents, saved checkpoints, and dated reports.

In plain words
What is it for?
It is for full QA campaigns covering static code review, browser or API testing, fixes, redeployment checks, smoke tests, and locale checks.
Why use it?
Testing a real product across code and live behavior is easy to perform inconsistently, especially when fixes and retesting are spread across sessions. This defines a guarded process with explicit verification before claiming completion.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the daily-tools plugin — 9 skills shipped together

Good fit It is for full QA campaigns covering static code review, browser or API testing, fixes, redeployment checks, smoke tests, and locale checks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/smk-labs/claude-plugins/swarm-qa
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.

Any agent
npx skills add smk-labs/claude-plugins --skill swarm-qa
Clone the repo
git clone --depth 1 https://github.com/smk-labs/claude-plugins

Made for: Claude Code.

Or install daily-tools, the plugin that ships this one along with the rest of its 9 skills.

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.

agentmods badge for swarm-qa

README.md
[![agentmods](https://agentmods.dev/badge/skills/smk-labs/claude-plugins/swarm-qa.svg)](https://agentmods.dev/skills/smk-labs/claude-plugins/swarm-qa)
Your own site
<a href="https://agentmods.dev/skills/smk-labs/claude-plugins/swarm-qa"><img src="https://agentmods.dev/badge/skills/smk-labs/claude-plugins/swarm-qa.svg" alt="Measured on agentmods" height="20"></a>
Per session 140 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,104 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00140 $0.01104
Opus 5 $0.00070 $0.00552
Sonnet 5 $0.00028 $0.00221
Haiku 4.5 $0.00014 $0.00110

Measured 8d ago against content hash a20b6b38c748, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade C, and why

swarm-qa scanned grade C 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 8d 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

کارزار کامل «سوارم کیوای» روی یک محصول زنده با متد چهار فازی: ممیزی استاتیک سوارمی کد، کیوای عمیق زنده، سوارم فیکس، و کیوای تأیید نهایی. با چک‌پوینت روی دیسک و گزارش تاریخ‌دار. Use when the user says "سوارم کیوای", "سوار
daily-tools/skills/swarm-qa/SKILL.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

swarm-qa: کیوای سوارمی چهار فازی

هدف: همان مأموریتی که قبلا هر بار با یک پرامپت ده‌هزار کاراکتری ساخته می‌شد، حالا با یک کلمه. تو ارکستراتور هستی: قضاوت و طراحی با تو، اجرای گسترده با ایجنت‌های Sonnet، بررسی عمیق با Opus.

پیش‌پرواز

  1. اول .claude/swarm-qa.local.md پروژه را بخوان (فرمت پایین). هرچه آنجا هست دوباره نپرس.
  2. کمبودها را در یک پرسش batched بگیر: آدرس‌ها و استک، منبع کردهای تست (فقط مسیر فایل یا نام env؛ مقدار سیکرت هرگز در چت تکرار نشود)، سقف‌های همزمانی (پیش‌فرض: مرورگر 1، کال‌های سنگین 8)، فایل known-issues، و دامنهٔ ممنوعه.
  3. کانفیگ نهایی را در همان فایل ذخیره کن تا دفعهٔ بعد پرسش صفر شود.

قوانین سخت (در همهٔ فازها)

  • مرورگر یک surface مشترک است: همیشه فقط یک ایجنت مرورگر زنده. فن‌اوت وسیع فقط برای کار read-only و کد و API.
  • دادهٔ پروداکشن read-mostly است. نوشتن فقط روی دادهٔ تست مشخص‌شده.
  • بیلد و دیپلوی فقط روی سرور، نه لپ‌تاپ. بعد از هر دیپلوی smoke test و چک locale.
  • سشن‌ها و پروسه‌های زندهٔ کاربر هرگز kill یا overwrite نمی‌شوند.
  • هیچ ادعای «انجام شد» بدون verify واقعی (نه استاب).

چهار فاز (با ابزار Workflow؛ هر فاز یک ورک‌فلوی جدا تا بین فازها در جریان بمانی)

  1. ممیزی استاتیک: سوارم گستردهٔ Sonnet روی خود کد، بدون مرورگر. هر ایجنت یک برش عمودی: auth، پرداخت، فرم‌ها، i18n و RTL، پرفورمنس، امنیت. خروجی: یافته‌های حدسی با اسکیمای پایین.
  2. کیوای زنده: ایجنت‌های کم‌تعداد اما عمیق (Opus) روی محصول واقعی. لاین مرورگر سریالی. فلوهای اصلی کاربر تا انتها (ورود تا خرید). یافته‌های فاز 1 را هم راستی‌آزمایی کن.
  3. سوارم فیکس: فقط یافته‌های تأییدشدهٔ P0 تا P2. هر یافته یک ایجنت فیکس؛ در صورت برخورد فایل‌ها worktree ایزوله. ship small: هر فیکس کامیت جدا.
  4. تأیید نهایی: ایجنت‌های verify مستقل، هر فیکس در محیط واقعی، رگرشن‌چک فلوهای اصلی. اگر رد شد، یافته دوباره باز می‌شود و به فاز 3 برمی‌گردد.

اسکیمای یافته (خروجی ساخت‌یافتهٔ همهٔ ایجنت‌ها)

{surface, flow, severity: P0|P1|P2|P3, symptom, repro, evidence, root_cause, is_regression}

چک‌پوینت و تاب‌آوری

  • مسیر کارزار: reports/swarm-qa/<YYYY-MM-DD>/. بعد از هر فاز و هر 10 یافته checkpoint.json آپدیت شود.
  • بعد از قطعی: اول checkpoint و resumeFromRunId ورک‌فلو. هیچ فازی از صفر تکرار نمی‌شود.

Read the full file on GitHub · 54 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. 8d ago First seen · 54 lines · 140 tokens per session scan C a20b6b38c748

Subscribe to this mod's changes

swarm-qa is a skill published in the GitHub repository smk-labs/claude-plugins (11 stars, last pushed 3d ago), licensed MIT. It adds 140 tokens to every session and 1,104 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

testing-and-quality

Use throughout the build and before claiming any phase or the project "done", to run the four mandatory quality gates and verify them with evidence. Covers the test pyramid, Playwright + Chrome DevTools browser verification, WCAG AA, and the commit/finish gate wiring.

martian56/claude-engineer · 58 tokens

maestro-flutter

Maestro E2E testing knowledge for Flutter apps. YAML-based flows, TestKeys, visual regression, Maestro MCP integration. Background knowledge for QE E2E testing phase.

aleksandr-chaika/flutter-clean-arch-skills · 41 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

test-scenarios

Create comprehensive test scenarios from user stories with test objectives, starting conditions, user roles, step-by-step actions, and expected outcomes. Use when writing QA test cases, creating test plans, defining acceptance tests, or preparing for feature validation.

phuryn/pm-skills · 52 tokens

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.

laolaoshiren/claude-code-skills-zh · 86 tokens

agent-browser

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

code-yeongyu/oh-my-openagent · 51 tokens