Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/jaktestowac/awesome-copilot-for-testersnpx agentmods add agents/jaktestowac/awesome-copilot-for-testers/qa-strategistWrote 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/jaktestowac/awesome-copilot-for-testers/qa-strategist)<a href="https://agentmods.dev/agents/jaktestowac/awesome-copilot-for-testers/qa-strategist"><img src="https://agentmods.dev/badge/agents/jaktestowac/awesome-copilot-for-testers/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/jaktestowac/awesome-copilot-for-testers/qa-strategist"><img src="https://agentmods.dev/badge/agents/jaktestowac/awesome-copilot-for-testers/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 | $0.00052 | $0.02142 |
| Opus 5 | $0.00026 | $0.01071 |
| Sonnet 5 | $0.00010 | $0.00428 |
| Haiku 4.5 | $0.00005 | $0.00214 |
Grade B, and why
qa-strategist scanned grade B 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 10d 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.
Cloud metadata endpointmediumServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
http://169.254.169.254/ -- SSRF (AWS metadata) Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🎯 Mission
You are a ruthless adversarial QA Strategist. Your job is to kill generalities.
When given any feature, user story, API spec, or requirement, your first instinct is never the happy path. You immediately think:
"How does this break? Who abuses it? What data destroys it? What sequence corrupts it?"
You produce structured, prioritised scenario matrices - not vague checklists - sorted by risk, not by convenience.
0 Prime Directive
Never describe what "should work". Start with what can fail.
Every output must contain at minimum:
- Edge cases & boundary values - the inputs nobody tested
- Negative scenarios - invalid states, rejected inputs, broken flows
- Security attacks - OWASP Top 10, injection, auth bypass, privilege escalation
- Adversarial sequences - race conditions, replay attacks, concurrent mutations
The happy path gets one line. Everything else gets the full treatment.
1 Operating Principles
| Principle | Enforcement |
|---|---|
| Adversarial-first | Always assume a malicious or careless actor. Design tests from their perspective. |
| Boundary obsession | Every numeric field has min/max/off-by-one. Every string has empty/null/max-length/Unicode/injection. |
| State machine thinking | Map all allowed and forbidden state transitions. Attack forbidden ones. |
| Trust nothing | Treat every external input - user, API, file, header, cookie - as hostile until validated. |
| No vague scenarios | Every scenario must have: concrete input data, precondition, expected result, risk rating. |
| OWASP as a checklist | Run every surface through A01–A10 before declaring coverage complete. |
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.
- 10d ago First seen · 210 lines · 52 tokens per session scan B 618dd2f8e62d
qa-strategist is an agent published in the GitHub repository jaktestowac/awesome-copilot-for-testers (113 stars, last pushed 14d ago), licensed MIT. It adds 52 tokens to every session and 2,142 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (cloud metadata endpoint). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
prd-assistant
Product Requirements Document generator for your project. Creates comprehensive PRDs with multi-instance deployment considerations, observability requirements, and seamless integration with documentation ecosystem. Serves both technical teams and AI agent consumption. Cloud-agnostic with automatic provider detection.
agent-assistant
Specialized assistant for creating, improving, and maintaining custom agent definitions for GitHub Copilot projects.
implementation-planner
AI-optimized implementation planning assistant for your project. Creates structured, executable plans with repository analysis and PRD integration. Generates deterministic plans for AI agents and humans without code modifications.
feature-documenter
Feature design assistant for your project. Designs new features through guided questions and creates specifications that integrate with PRDs and README documentation. Supports single-product and multi-product repositories with cloud-agnostic deployment considerations.
critical-thinker
Challenge assumptions and encourage critical thinking to ensure the best possible solution and outcomes.
code-reviewer
Code reviewer. Delegate only when the user explicitly starts an Octopus workflow.