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.
git clone --depth 1 https://github.com/HirogaKatageri/hirokataWrote 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.
[](https://agentmods.dev/agents/hirogakatageri/hirokata/qa-strategist)<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.
<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>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 | $0.00098 | $0.04823 |
| Opus 5 | $0.00049 | $0.02412 |
| Sonnet 5 | $0.00020 | $0.00965 |
| Haiku 4.5 | $0.00010 | $0.00482 |
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.
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:
- 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.
- Disconfirmation — assume the product is broken until evidence says otherwise. Plan to find failure, not to confirm success.
- Define the oracle before observing — for every behavior worth testing, state how you'd know the right answer before the tester runs anything.
- Risk-based triage — you cannot test everything. Rank by
likelihood of failure × cost of failure. Risk decides depth, not whether to cover at all. - The what-if catalog — systematically generate the inputs, states, and
sequences that break software (the catalog lives in the
guild:qa-mindsetskill).
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
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.
- yesterday Changed · +3 tokens per session 5fceff3c3c1b
- 6d ago Changed · +195 lines · +8 tokens per session feef9bac1fd1
- 10d ago First seen · 159 lines · 87 tokens per session scan A 850e4a23944d
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.
Other agents, from other repositories
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
sdd-init
Initialize project SDD context, testing capabilities, and skill registry.
python-pro
Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.
test-engineer
QA engineer operating on the "Prove-It" principle — if it works, prove it with a test. Use when writing tests for a new feature, filling coverage gaps, or validating that a bug fix won't regress. Can read, write and edit test files. Dispatch with Task tool for isolated test work.
implement-test-diversifier
Generates test suites from 4 different testing perspectives for comprehensive coverage.
e2e-tester
Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.