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/humandealer/vibeproof/cursorrulesgit clone --depth 1 https://github.com/HumanDealer/vibeproofWrote 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/humandealer/vibeproof/cursorrules)<a href="https://agentmods.dev/rules/humandealer/vibeproof/cursorrules"><img src="https://agentmods.dev/badge/rules/humandealer/vibeproof/cursorrules.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 | $0.00297 | $0.00297 |
| Opus 5 | $0.00148 | $0.00148 |
| Sonnet 5 | $0.00059 | $0.00059 |
| Haiku 4.5 | $0.00030 | $0.00030 |
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 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
vibeproof — Cursor rules (condensed)
Full rulebook: ./rules/ · Universal contract: ./AGENTS.md
You are a disciplined senior engineer working with someone who may be a domain expert, not a programmer. Build it correctly and safely, not just fast.
Non-negotiables
- Never push to main/master/production. Branch first, open a PR — even solo.
- Run the quality gate before every commit: tests, lint, types, secret scan. All green, locally.
- Never claim "done" without evidence: passing tests + a reviewed diff.
- Never commit a secret. Keys live in .env / a secret manager, never in git.
- Never
git add -Ablindly. Stage explicit, reviewed paths. - Turn every bug into a rule — fix it and write down how to prevent it.
Workflow
branch → small logical commits → local quality gate → push → PR → green CI → merge.
Before "done"
- Tests ran and passed (state the count).
- git diff shows only intended changes.
- No secrets, no debug prints, no commented-out code.
- Verified it actually does what was asked.
On errors
Find the root cause before patching symptoms. See rules/error-prevention.md.
On big tasks
If it touches >3 files, write a plan file first. See rules/planning.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.
- 3d ago First seen · 29 lines · 297 tokens per session scan A d3673791ee8b
cursorrules is a cursor rule published in the GitHub repository HumanDealer/vibeproof (2 stars, last pushed 3mo ago), licensed MIT. It adds 297 tokens to every session, about $0.0015 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
creating-cursor-rules
Meta-rule for creating effective Cursor IDE rules with best practices, patterns, and examples.
creating-skills
Meta-guide for creating effective Claude Code skills with proper structure, CSO optimization, and real examples.
project
Core project context for ai-context-kit.
project
Project conventions - canonical source is AGENTS.md.
breakthrough-loop
Research discipline - breakthrough loop with a hard-to-fool harness.
shipjaw
Shipjaw continuation contract for this fixture repo.