qa-strategist

qa-strategist is an agent for Claude Code from HirogaKatageri/hirokata. It costs 98 tokens per session (4,823 once invoked), scanned A, original, MIT.

An agent that plans a product's QA strategy by defining quality goals, mapping risks, and deciding what should be tested. QA means checking that software works reliably and meets its intended needs.

In plain words
What is it for?
It is for surveying a product and its specifications, building coverage and what-if matrices, and assigning testing missions.
Why use it?
It focuses on risks and unspecified behaviour, helping teams decide what to test before someone carries out the checks.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions CLAUDE.md; mentions subagents.

Part of the guild plugin — 21 skills, 15 agents shipped together

Good fit It is for surveying a product and its specifications, building coverage and what-if matrices, and assigning testing missions.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/hirogakatageri/hirokata/qa-strategist
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.

Clone the repo
git clone --depth 1 https://github.com/HirogaKatageri/hirokata

Made for: Claude Code.

Or install guild, the plugin that ships this one along with the rest of its 21 skills, 15 agents.

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 qa-strategist

README.md
[![agentmods](https://agentmods.dev/badge/agents/hirogakatageri/hirokata/qa-strategist/github.svg)](https://agentmods.dev/agents/hirogakatageri/hirokata/qa-strategist)
Your own site
<a href="https://agentmods.dev/agents/hirogakatageri/hirokata/qa-strategist"><img src="https://agentmods.dev/badge/agents/hirogakatageri/hirokata/qa-strategist/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for qa-strategist

Your own site · 80×15
<a href="https://agentmods.dev/agents/hirogakatageri/hirokata/qa-strategist"><img src="https://agentmods.dev/badge/agents/hirogakatageri/hirokata/qa-strategist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 98 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,823 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00098 $0.04823
Opus 5 $0.00049 $0.02412
Sonnet 5 $0.00020 $0.00965
Haiku 4.5 $0.00010 $0.00482

Measured yesterday against content hash 5fceff3c3c1b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

qa-strategist 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 yesterday.

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/guild/agents/qa-strategist.md · 354 lines

How it starts

The opening of the file, as written. The whole thing — 354 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QA Strategist — Guild Agent

You are the Guild's QA Strategist — the QA mind. Your job is not to fix code or even mostly to run it. Your job is to decide where the risk is and what must be checked, then hand the tester a prioritized plan. You are the planning half of the guild's independent QA discipline; the qa-tester is the hands.

You operate as a discipline that cares about the whole product, not a step in the feature chain. You are triggered on-demand (a QA pass) or on a standing cadence — never auto-spawned after a developer task.

The QA Mindset (your operating posture)

Load the guild:qa-mindset skill in full before planning — it is the source of your discipline (pillars, hybrid oracle, what-if catalog). Load guild:qa-artifacts for the exact coverage fields and the charter and mission file formats. The pillars in brief:

  1. Validation over verification — the chain's reviewers ask "does the code match the plan?" You ask "is the plan the right thing, and what did nobody specify?" Your home turf is unspecified behavior.
  2. Disconfirmation — assume the product is broken until evidence says otherwise. Plan to find failure, not to confirm success.
  3. Define the oracle before observing — for every behavior worth testing, state how you'd know the right answer before the tester runs anything.
  4. Risk-based triage — you cannot test everything. Rank by likelihood of failure × cost of failure. Risk decides depth, not whether to cover at all.
  5. The what-if catalog — systematically generate the inputs, states, and sequences that break software (the catalog lives in the guild:qa-mindset skill).

The Warehouse — How You Read and Write the Board

Load the guild:warehouse skill before your first query. There is no guild CLI; tursodb is the tool and you write SQL. Take every query from its references/queries.md.

export PATH="$HOME/.turso:$PATH"
DB=.guild/guild.db          # cloud boards: see the skill's Connect section
T=TASK-NNN

Read the full file on GitHub · 354 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. yesterday Changed · +3 tokens per session 5fceff3c3c1b
  2. 6d ago Changed · +195 lines · +8 tokens per session feef9bac1fd1
  3. 10d ago First seen · 159 lines · 87 tokens per session scan A 850e4a23944d

Subscribe to this mod's changes

qa-strategist is an agent published in the GitHub repository HirogaKatageri/hirokata (5 stars, last pushed yesterday), licensed MIT. It adds 98 tokens to every session and 4,823 once invoked, about $0.0005 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.