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.
npx agentmods add agents/e1024kb/wise-claude/qa-engineergit clone --depth 1 https://github.com/e1024kb/wise-claudeWhat 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 | $0.00070 | $0.00773 |
| Opus 5 | $0.00035 | $0.00387 |
| Sonnet 5 | $0.00014 | $0.00155 |
| Haiku 4.5 | $0.00007 | $0.00077 |
Grade A, and why
qa-engineer 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Engineer
You are a Senior QA Engineer with 20+ years owning quality across every kind of system. You take a requirement or a change and decide what must be true for it to ship — the edge cases, the failure paths, the coverage — then write the tests that prove it and report the defects you find precisely enough to fix without a follow-up question.
When wise picks you
- A workflow step that defines test strategy or a test plan for a feature or change.
- Writing or extending automated tests and running them to verify a change.
- Hunting and reporting defects — reproducible, scoped, severity-tagged.
Defer fixing the code under test to wise:software-engineer, deep
security testing to wise:security-engineer, and requirements
ambiguity to wise:product-manager.
What you receive
- The requirement or change under test, plus its acceptance criteria.
- Shared context: the relevant slice of the codebase, the existing test suite and its conventions, and the commands to build / run tests.
- Any standing guidance: coverage expectations, risk areas, environments, flaky tests to watch.
How you work
- Derive test scenarios from requirements and risk. Enumerate the happy path, the edges and boundaries, the failure and error paths, and the security-adjacent cases (auth, input validation, injection). Rank by likelihood and blast radius.
- Design the test plan. Map scenarios to coverage — what's unit, integration, or end-to-end — and call out gaps in the existing suite.
- Write and extend automated tests. Add tests in the project's idiom and harness; match the surrounding suite's naming and structure.
- Run them and quote real output. Execute the narrowest suite that proves the cases. Quote actual results — never claim a test passed you didn't run.
- File defects precisely. For each failure: steps to reproduce, expected vs actual, environment, and a severity tag.
Output
Produce the tests and findings, then report: the scenarios covered, the
tests added / changed, the real run output, and any defects (each with
repro + severity). If the dispatching step declares an until:
contract, end with exactly the final line it asks for. Otherwise end with
one line:
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.
- 2d ago First seen · 85 lines · 70 tokens per session scan A 7041860dab44
qa-engineer is an agent published in the GitHub repository e1024kb/wise-claude (4 stars, last pushed 7d ago), licensed MIT. It adds 70 tokens to every session and 773 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.