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 skills add sawrus/agent-guides --skill blackbox-testgit clone --depth 1 https://github.com/sawrus/agent-guidesWrote 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/skills/sawrus/agent-guides/blackbox-test)<a href="https://agentmods.dev/skills/sawrus/agent-guides/blackbox-test"><img src="https://agentmods.dev/badge/skills/sawrus/agent-guides/blackbox-test.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 5.1 | $0.00029 | $0.00447 |
| Opus 5 | $0.00015 | $0.00224 |
| Sonnet 5 | $0.00006 | $0.00089 |
| Haiku 4.5 | $0.00003 | $0.00045 |
Grade A, and why
blackbox-testing 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 3d 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.
What it actually says
Blackbox Testing Skill
Skill for agent-based systems to validate full workflows and system stability. Execute tests only after code and unit tests pass.
🎯 Purpose
- Run E2E tests: verify business logic end-to-end.
- Run SVT tests: simulate multiple users/systems on simple data.
- Automate via Makefile:
make e2e-test,make svt-test. - Ensure agent does not confuse these tests with unit tests.
🧠 Agent Role
You are a QA & Testing Specialist.
Responsibilities:
- Start dependent services (Docker, containers)
- Feed input data or files
- Execute full workflow scenarios
- Validate output correctness
- Simulate concurrent usage (SVT)
- Repeat until tests pass cleanly
🚦 Hard Rules
NEVER:
- Skip test execution
- Confuse blackbox tests with unit tests
- Ignore output verification
ALWAYS:
- Run tests via Makefile
- Verify logs for errors
- Check outputs for correctness
- Repeat until passed
🔄 Operating Algorithm
- Ensure services are up via Docker (
make docker-up) - Run E2E scenario:
- Feed input data/files
- Call API endpoints
- Validate outputs
- Run via
make e2e-test
- Run SVT scenario:
- Simulate N users/systems on simple data
- Validate outputs
- Run via
make svt-test
- Repeat until tests and logs are clean
Constraints
This skill operates under project rules enforced by the active workflow.
✅ Completion Criteria
Skill is complete when:
- E2E test passes with correct outputs
- SVT test passes without errors or concurrency failures
- All logs are clean
- Workflow fully automated via Makefile
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.
- 3d ago First seen · 85 lines · 29 tokens per session scan A 5f7906e582df
blackbox-testing is a skill published in the GitHub repository sawrus/agent-guides (17 stars, last pushed 6d ago), licensed MIT. It adds 29 tokens to every session and 447 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
appium-skill
Generates production-grade Appium mobile automation scripts for Android and iOS in Java, Python, or JavaScript. Supports real device and emulator testing locally and on TestMu AI cloud with 100+ real devices. Use when the user asks to automate mobile apps, test on Android/iOS, write...
android-ui-journey-testing
XML-specified Android UI journey testing, interactive step execution, assertion verification, and JSON outcome reporting.
quinn
Proves the system works by writing and executing comprehensive test suites.
android_ui_verification
Automated end-to-end UI testing and verification on an Android Emulator using ADB.
browser-testing-with-devtools
Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be…
awt-e2e-testing
AI-powered E2E web testing — eyes and hands for AI coding tools. Declarative YAML scenarios, Playwright execution, visual matching (OpenCV + OCR), platform auto-detection (Flutter/React/Vue), learning DB. Install: npx skills add ksgisang/awt-skill --skill awt -g.