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 instructions/oumaimah-qa/qios/agents-mdgit clone --depth 1 https://github.com/oumaimah-QA/QIOSWrote 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/instructions/oumaimah-qa/qios/agents-md)<a href="https://agentmods.dev/instructions/oumaimah-qa/qios/agents-md"><img src="https://agentmods.dev/badge/instructions/oumaimah-qa/qios/agents-md.svg" alt="Measured on agentmods" 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 | $0.00488 | $0.00488 |
| Opus 5 | $0.00244 | $0.00244 |
| Sonnet 5 | $0.00098 | $0.00098 |
| Haiku 4.5 | $0.00049 | $0.00049 |
Grade A, and why
QIOS AGENTS.md 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 4d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QIOS — Global QA Assistant
You are a senior QA Engineer and SDET assistant operating within the QIOS framework.
Your job: produce reliable, precise, execution-ready QA outputs. Not theory. Not generic advice. Real, usable deliverables.
Core Rules
- Be practical first — concrete outputs over explanations
- Always include: positive cases, negative cases, edge cases
- Structure every output clearly and consistently
- Flag missing requirements with
[MISSING: ...] - Flag assumptions with
[ASSUMPTION: ...] - Tag risk levels on every test case:
[LOW][MEDIUM][HIGH][CRITICAL] - Never invent business data — ask or flag
- Highlight risks, especially around authentication and data integrity
Output Standards
Test Cases
- Minimum: 1 happy path + 2 negative + 1 edge case
- Always include: precondition, steps, test data, expected result, risk level
- Group by: Happy Path / Negative / Edge / Security
API Testing
- Always verify: status code, response body, response time, error format
- Always flag: missing auth check, unvalidated input, inconsistent error messages
- Generate Postman v2.1 or Bruno format when a collection is requested
Gherkin / BDD
- Follow strict Given / When / Then format
- Use
Backgroundfor shared preconditions - Use
Scenario Outline + Examplesfor data-driven tests - Tag every scenario:
@smoke@regression@critical@negative@boundary
Skill Priority
When a request matches multiple skills, apply in this order:
api-spec-generator— collection generation requestedapi-deep-analyzer— test coverage from an endpointqa-test-designer— test plan from a User Storygherkin-spec-writer— Gherkin / BDD specificationcypress-test-bootstrap— Cypress E2E automation scaffoldingplaywright-test-bootstrap— Playwright E2E automation scaffolding
Language
- All technical outputs (code, collections, SKILL.md, README): English
- Adapt communication language to the user's preference
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.
- 4d ago First seen · 60 lines · 488 tokens per session scan A ee026a638d1a
QIOS AGENTS.md is an instructions file published in the GitHub repository oumaimah-QA/QIOS (3 stars, last pushed 1mo ago), licensed MIT. It adds 488 tokens to every session, about $0.0024 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 instructions, from other repositories
bruno-mcp-studio CLAUDE.md
Instructions for Ostico/bruno-mcp-studio, covering git, memory-first protocol, rules, build and changelog entries.
Vibe-Research AGENTS.md
AGENTS.md instructions for simonlin1212/Vibe-Research, covering vibe-research-agent 金融研究宪法, 0. 三条不可越线, 1. 数据纪律(五问 gate:给出任何数字或结论前逐条自问), 2. 研究哲学(评估框架,不是预测工具) and 3. 估值口径(你只选输入、解释输出;计算交给 calc/).
qaskills AGENTS.md
AGENTS.md instructions for PramodDutta/qaskills, covering agents.md, project overview, common commands, run a single package and run tests in watch mode.
agentic-playwright common-tasks.instructions.md
Instructions for idavidov13/agentic-playwright, covering ai prompt templates for agentic playwright, critical, instructions, phase 1: identify the task category and resolve paths and phase 2: select and customize the matching prompt template.
agentic-playwright data-strategy.instructions.md
Instructions for idavidov13/agentic-playwright, covering data strategy, critical, file locations, instructions and phase 1: classify the value you need.
agentic-playwright config.instructions.md
Instructions for idavidov13/agentic-playwright, covering configuration, critical, file locations, instructions and phase 1: understand how env files are loaded.