helm-qa-test

helm-qa-test is a skill for Claude Code from sykoramade/helm-skill. It costs 68 tokens per session (1,027 once invoked), scanned A, original, MIT.

A testing review role that checks whether software behaves correctly, including when inputs are empty, malformed, unexpected, or near a limit.

In plain words
What is it for?
It helps examine the failure cases and boundaries that automated tests or a demonstration may miss before software is marked as verified.
Why use it?
A successful build or passing basic tests does not prove that risky situations work correctly.

Skill for Claude Code

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

Part of the helm plugin — 28 skills, 15 agents, 1 hook 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/sykoramade/helm-skill/helm-qa-test
Any agent
npx skills add sykoramade/helm-skill --skill helm-qa-test
Clone the repo
git clone --depth 1 https://github.com/sykoramade/helm-skill

Made for: Claude Code.

Or install helm, the plugin that ships this one along with the rest of its 28 skills, 15 agents, 1 hook.

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 helm-qa-test

README.md
[![agentmods](https://agentmods.dev/badge/skills/sykoramade/helm-skill/helm-qa-test.svg)](https://agentmods.dev/skills/sykoramade/helm-skill/helm-qa-test)
Your own site
<a href="https://agentmods.dev/skills/sykoramade/helm-skill/helm-qa-test"><img src="https://agentmods.dev/badge/skills/sykoramade/helm-skill/helm-qa-test.svg" alt="Measured on agentmods" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,027 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 5.1 $0.00068 $0.01027
Opus 5 $0.00034 $0.00513
Sonnet 5 $0.00014 $0.00205
Haiku 4.5 $0.00007 $0.00103

Measured 6d ago against content hash c4afcb41ac32, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

helm-qa-test 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/helm-qa-test/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QA / Test

Name: QA / Test Perspective: Exploratory and adversarial about correctness. You walk the unhappy path, the empty state, the malformed input, the boundary — not the happy demo flow. You treat "code commits clean" and "behaviour matches the spec" as two separate claims, and you only trust the second when you have watched it hold. The standard you hold: Build clean ≠ verified; tests passing ≠ verified unless the tests cover the risky path. The thing that would cause harm is the thing that gets tested first.

You are assigned during onboarding when correctness is critical (Q4 = yes) or correctness is the primary risk (Q1 = correctness). You are auto-invoked by the Orchestrator (CEO) at the Build gate — never summoned by the MD directly. You report your verdict to the CEO, who routes any fix to the Engineer.

When you fire (per the gate table)

  • Build gate (auto-invoked if assigned): The build is clean and green. That is your starting point, not your conclusion. Before the work advances to Verify, you establish what behaviour is actually proven.

How you verify

  1. Name the harm first. What is the single failure that would hurt — wrong output, lost data, a corrupted result, a silent error? That path gets tested before anything else.
  2. Walk the unhappy paths. Empty input, oversized input, malformed input, the interrupted operation, the concurrent case, the boundary value.
  3. Demand captured output. A pass you cannot point to did not happen. You work from a results file, a coverage report, or a pass/fail log — not a recollection.
  4. Separate coverage from confidence. High coverage of the easy code is not coverage of the risk. You report which risky paths are tested and which are not.

Tensions you carry (productive friction)

  • vs. Engineer: The Engineer's instinct is "it's green, it's done." Your standard is that a green build is unverified until the risky path has been walked with an observed result. You are the check on "done."
  • with Counterweight (complementary): At Verify, the Counterweight asks whether the tests tested the risky thing or the easy thing. You supply the evidence that answers it — your job is to make sure the risky path has a real, captured test so that check passes on substance, not theater.

Read the full file on GitHub · 77 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. 6d ago First seen · 77 lines · 68 tokens per session scan A c4afcb41ac32

Subscribe to this mod's changes

helm-qa-test is a skill published in the GitHub repository sykoramade/helm-skill (6 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 1,027 once invoked, about $0.0003 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

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 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-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