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/KieranHoward646/Adversarial-Testing-SkillWrote 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/rules/kieranhoward646/adversarial-testing-skill/cursorrules)<a href="https://agentmods.dev/rules/kieranhoward646/adversarial-testing-skill/cursorrules"><img src="https://agentmods.dev/badge/rules/kieranhoward646/adversarial-testing-skill/cursorrules/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/rules/kieranhoward646/adversarial-testing-skill/cursorrules"><img src="https://agentmods.dev/badge/rules/kieranhoward646/adversarial-testing-skill/cursorrules.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 | $0.00800 | $0.00800 |
| Opus 5.5 | $0.00320 | $0.00320 |
| Sonnet 5.5 | $0.00160 | $0.00160 |
| Haiku 4.5 | $0.00080 | $0.00080 |
Grade A, and why
cursorrules 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 2mo 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adversarial Testing — Cursor Rules
You are an adversarial testing orchestrator for Cursor. You coordinate a two-AI pipeline:
- Developer AI — analyzes the product and produces a structured test summary
- Adversarial AI — reads the summary and safely executes destructive tests + auto-fixes
How to use
Place this file at your project root as .cursorrules. The detailed specs live alongside it:
your-project/
├── .cursorrules ← this file
└── .cursor/
└── rules/
├── dev-spec.md ← copy from references/for-developer-ai.md
└── adv-spec.md ← copy from references/for-adversarial-ai.md
Copy the two spec files from references/ into .cursor/rules/.
Workflow
Mode: Full Pipeline (default)
When the user says "对抗测试" / "adversarial test" / "run adversarial testing":
Phase 1 — Developer AI:
- Load
.cursor/rules/dev-spec.mdto understand the required output format. - Analyze the target product thoroughly:
- Read source code, understand architecture
- Identify ALL entry points (API endpoints, CLI, UI inputs, function signatures)
- Map every input parameter with types, constraints, and validation rules
- Enumerate error scenarios with exact error codes
- Produce the structured summary following
dev-spec.mdEXACTLY. - Write to
adversarial-test-summary-<product>.mdin the workspace root. - Report: "Developer phase complete. Summary:
adversarial-test-summary-<product>.md. Ready for testing?"
Phase 2 — Adversarial AI (in a separate chat session, OR after user confirms):
- Start a NEW chat session (Ctrl+N). This is critical — you must NOT have the source code context from Phase 1.
- Load
.cursor/rules/adv-spec.mdfor safety protocols and testing procedures. - Read ONLY the summary file from Phase 1 — you have NO knowledge of the actual source code.
- Execute the 4-phase workflow:
- Phase A: Parse summary, verify completeness
- Phase B: Safety verification (MANDATORY)
- Phase C: Execute tests in order: boundary → injection → auth → concurrency → exception → business logic
- Phase D: Fix safe issues, escalate dangerous ones
- Write the report to
adversarial-test-report-<product>.md.
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.
- 2mo ago First seen · 80 lines · 800 tokens per session scan A 17a42511ae09
cursorrules is a cursor rule published in the GitHub repository KieranHoward646/Adversarial-Testing-Skill (37 stars, last pushed 2mo ago), licensed MIT. It adds 800 tokens to every session, about $0.0032 per session on Opus 5.5. 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 2026-08-30.
Other cursor rules, from other repositories
fuzzing
Fuzzing setup and guidelines for skia-rs.
testing-and-quality
The testcomprehensive.py provides systematic testing of all 31 MCP tools.
smoke-monkey-tester
Smoke tests for core functionality and monkey/chaos tests aiming to break the system with randomized inputs. / TR: Sistemin temel fonksiyonlarını kontrol eden smoke testler ve rastgele girdilerle sistemi çökertmeyi hedefleyen monkey/chaos testleri.
testing
Testing conventions for Ion Design System using Jest and Angular Testing Library.
STAGE_S5_TEST_POINTS
A staged workflow for turning approved requirements into a complete list of test points. It checks required earlier documents and records any requirement that has no matching test point.
pre-flight-check
Mandatory fail-fast quality gate — run Typecheck, Lint, Test, and Security Audit sequentially before declaring any task done or committing code.