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/trianglegrrl/promptonomicon/cursor-rulesgit clone --depth 1 https://github.com/trianglegrrl/promptonomiconWrote 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/trianglegrrl/promptonomicon/cursor-rules)<a href="https://agentmods.dev/rules/trianglegrrl/promptonomicon/cursor-rules"><img src="https://agentmods.dev/badge/rules/trianglegrrl/promptonomicon/cursor-rules.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 | $0.00334 | $0.00334 |
| Opus 5 | $0.00167 | $0.00167 |
| Sonnet 5 | $0.00067 | $0.00067 |
| Haiku 4.5 | $0.00033 | $0.00033 |
Grade A, and why
cursor-rules 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.
What it actually says
Promptonomicon Framework
This project uses the Promptonomicon framework for structured, documentation-driven development.
Primary Rule
For ALL new features, bug fixes, or significant changes:
Follow the Promptonomicon process defined in .promptonomicon/PROMPTONOMICON.md
Process Overview
- Understand - Investigate requirements thoroughly
- Design - Create design documentation in
ai-docs/ai-design/ - Plan - Build implementation plan in
ai-docs/ai-plans/ - Develop - Execute with test-driven development
- Document - Capture reality in
ai-docs/ai-implementation/ - Update - Synchronize all documentation
Key Principles
- Documentation-driven development
- Fail-hard policy (no silent failures)
- Test coverage requirements at each step
- Clean code practices (SOLID, DRY, KISS)
MCP Servers Available
- versionator: Use for checking latest package versions
- context7: Use for fetching current library documentation (if API key configured)
File Naming
Use datestamps: date +%Y%m%d
- Design:
ai-docs/ai-design/YYYYMMDD_design_feature_name.md - Plan:
ai-docs/ai-plans/YYYYMMDD_plan_feature_name.md - Implementation:
ai-docs/ai-implementation/YYYYMMDD_implementation_feature_name.md
Scratch Directory
Use .scratch/ for temporary work and track progress in .scratch/todo.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.
- 4d ago First seen · 44 lines · 334 tokens per session scan A b56e60ebae1b
cursor-rules is a cursor rule published in the GitHub repository trianglegrrl/promptonomicon (7 stars, last pushed 6mo ago), licensed MIT. It adds 334 tokens to every session, about $0.0017 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 cursor rules, from other repositories
tdd
Final Verification: Always use: go test -v ./backend/api/handler/... | grep FAIL.
workflow
BDD-style workflow, UI screenshots in the PR, HTTP OpenAPI and config schema sync before lint, final checks.
agent-routing.pi-input-intercept
Codex 模型經 Pi machine dispatch 提出問題時的攔截、評估、代答或升級 protocol；觸及 spectra change / screenshot 情境時 path-scoped 載入.
mcpnuke-tests
Test conventions for mcpnuke — enforces TDD workflow.
tdd-workflow
Test-Driven Development workflow for implementing features. Activate when writing code — guides through the red-green-refactor cycle.
testing-discipline
TDD, BDD, and testing best practices — stack-agnostic.