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 rules/raydestar/sir-thaddeus/testinggit clone --depth 1 https://github.com/raydeStar/sir-thaddeusWhat 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 | $0.00239 | $0.00239 |
| Opus 5 | $0.00120 | $0.00120 |
| Sonnet 5 | $0.00048 | $0.00048 |
| Haiku 4.5 | $0.00024 | $0.00024 |
Grade A, and why
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 yesterday.
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
Testing Contract
Running Tests
- Do NOT invent test commands. Always use the harness scripts.
- Run tests via PowerShell from repo root:
./dev/test.ps1 - To run a subset:
./dev/test.ps1 -Filter "FullyQualifiedName~MyClass" - Full suite (Release + restore):
./dev/test_all.ps1 - First-time setup:
./dev/bootstrap.ps1
After Making Changes
- Re-run
./dev/test.ps1after every code change until it exits 0. - If tests fail, read the console output and fix the code.
- TRX reports are in
./artifacts/test-results/for detailed inspection.
Test Discipline
- Do NOT add new tests unless explicitly asked.
- Do NOT delete or skip existing tests to make the suite pass.
- If
dotnetSDK mismatch occurs, checkglobal.jsonand align. - If
./dev/test.ps1does not exist, create it perdocs/TESTING.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.
- yesterday First seen · 29 lines · 239 tokens per session scan A a035ab34bfcc
testing is a cursor rule published in the GitHub repository raydeStar/sir-thaddeus (13 stars, last pushed 8d ago), licensed Apache-2.0. It adds 239 tokens to every session, about $0.0012 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 2026-08-30.
Other cursor rules, from other repositories
honcho_rules
Honcho persistent memory — capture every conversation, recall past context, and build a growing model of the user. Activates on every conversation.
netllm
Route netllm install, editor connect, swarm, troubleshoot, PR/release, and macOS CI requests to project skills and docs.
swift-development
Swift development: SwiftUI, Combine, async/await, iOS patterns, and Apple platform conventions.
cursorrules
When the user asks about social media, use social-media-ai-mcp tools: schedulepost, generatehashtags, analyzeengagement, plancontentcalendar, getaudienceinsights.
cursorrules
This is an MCP (Model Context Protocol) server that provides Notion integration tools and AI agent workflows. Built with TypeScript, using the MCP SDK for server implementation.
lighter-safety
Safety contract for the Lighter MCP server. Apply whenever a lighter tool is invoked.