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/zhengbowenai-cmd/caliperWrote 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/zhengbowenai-cmd/caliper/cursor-rules)<a href="https://agentmods.dev/rules/zhengbowenai-cmd/caliper/cursor-rules"><img src="https://agentmods.dev/badge/rules/zhengbowenai-cmd/caliper/cursor-rules/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/zhengbowenai-cmd/caliper/cursor-rules"><img src="https://agentmods.dev/badge/rules/zhengbowenai-cmd/caliper/cursor-rules.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 | $0.00000 | $0.00454 |
| Opus 5.5 | $0.00000 | $0.00182 |
| Sonnet 5.5 | $0.00000 | $0.00091 |
| Haiku 4.5 | $0.00000 | $0.00045 |
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 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.
What it actually says
Caliper — Cursor rule
Use the caliper CLI when the user wants statistical evidence that a
prompt change is real, not just "feels better."
Trigger words
- "is this prompt better"
- "A/B test these prompts"
- "did my edit help"
- "find conflicts in this prompt"
- "which paragraph is dragging it down"
- 中文：新版 prompt / 真比旧版好 / 对比 / 测一测
Quick reference
# 1) Static check for rule conflicts (no LLM cost)
caliper lint path/to/prompt.md
# 2) Head-to-head A/B with confidence interval
caliper compare old.md new.md --eval cases.jsonl --run-dir runs/cmp
# 3) Auto-iterate with hard cost cap (no surprise bills)
caliper iterate seed.md --eval cases.jsonl --rounds 3 --max-cost-cny 50
# 4) Per-paragraph attribution
caliper analyze prompt.md --eval cases.jsonl
How to read the verdict
- BCa 95% CI excludes 0 → real change (positive or negative)
- BCa CI crosses 0 → noise; no statistical signal
- Hedges' g: 0.2 small · 0.5 medium · 0.8+ large
Aim for n ≥ 20 in eval cases for meaningful statistical power.
Eval JSONL format
{"id": "case-01", "input": "user prompt", "principle": "what's tested", "rubric": "0-10 grading"}
Repo
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 · 57 lines · 0 tokens per session scan A 5d3a3b02fe7f
cursor-rules is a cursor rule published in the GitHub repository zhengbowenai-cmd/caliper (2 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 454 tokens. 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
fuzzing
Fuzzing setup and guidelines for skia-rs.
testing
Testing conventions for Ion Design System using Jest and Angular Testing Library.
pre-flight-check
Mandatory fail-fast quality gate — run Typecheck, Lint, Test, and Security Audit sequentially before declaring any task done or committing code.
development-guidelines
⚠️ ALWAYS start with FREE tests before ANY paid content generation.
test
Rules for test files.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.