cursorrules

cursorrules is a cursor rule for Cursor from EmpiricaAI/empirica. It costs 1,717 tokens per session, scanned A, original, MIT.

A set of development rules for Empirica, a framework that records what an AI coding agent knows, assumes, and is unsure about during a task.

In plain words
What is it for?
Use it to start development sessions, record knowledge and uncertainty, follow the CASCADE workflow, and resume work with tracked context.
Why use it?
It makes uncertainty visible and helps the agent review its understanding before acting, rather than treating guesses as facts.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/empiricaai/empirica/cursorrules
Clone the repo
git clone --depth 1 https://github.com/EmpiricaAI/empirica

Made for: Cursor.

Wrote 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.

agentmods badge for cursorrules

README.md
[![agentmods](https://agentmods.dev/badge/rules/empiricaai/empirica/cursorrules.svg)](https://agentmods.dev/rules/empiricaai/empirica/cursorrules)
Your own site
<a href="https://agentmods.dev/rules/empiricaai/empirica/cursorrules"><img src="https://agentmods.dev/badge/rules/empiricaai/empirica/cursorrules.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,717 This file is loaded in full into every session.
When invoked 1,717 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.01717 $0.01717
Opus 5 $0.00859 $0.00859
Sonnet 5 $0.00343 $0.00343
Haiku 4.5 $0.00172 $0.00172

Measured 4d ago against content hash c3457d44280b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

.cursorrules · 208 lines

How it starts

The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Empirica - Epistemic Self-Assessment for AI Coding

You have Empirica installed - an epistemic self-awareness framework for AI agents. Use it to track what you KNOW vs what you're GUESSING during development work.

Core Principle

Epistemic transparency > Task completion speed

  • Track uncertainty explicitly (0.0-1.0 scale)
  • Learn systematically through CASCADE workflow
  • Resume efficiently across sessions

Quick Start

1. Start Session (AI-First JSON Mode)

echo '{"ai_id": "cursor-agent", "session_type": "development"}' | empirica session-create -
# Returns: {"ok": true, "session_id": "abc-123", ...}

2. CASCADE Workflow (Explicit Phases)

PREFLIGHT - Before starting work, assess what you know:

cat > preflight.json <<EOF
{
  "session_id": "abc-123",
  "vectors": {
    "engagement": 0.8,
    "foundation": {"know": 0.6, "do": 0.7, "context": 0.5},
    "comprehension": {"clarity": 0.7, "coherence": 0.8, "signal": 0.6, "density": 0.7},
    "execution": {"state": 0.5, "change": 0.4, "completion": 0.3, "impact": 0.5},
    "uncertainty": 0.4
  },
  "reasoning": "Starting with moderate knowledge, high uncertainty about X"
}
EOF
empirica preflight-submit < preflight.json

CHECK - During work, when uncertain (optional but recommended):

cat > check.json <<EOF
{
  "session_id": "abc-123",
  "confidence": 0.75,
  "findings": ["Found API pattern", "Learned OAuth2 flow"],
  "unknowns": ["Token refresh unclear"]
}
EOF
empirica check < check.json
# Returns: {"decision": "proceed"} or {"decision": "investigate_more"}

POSTFLIGHT - After work, measure what you learned:

cat > postflight.json <<EOF
{
  "session_id": "abc-123",
  "vectors": {
    "engagement": 0.9,
    "foundation": {"know": 0.85, "do": 0.9, "context": 0.8},
    "comprehension": {"clarity": 0.9, "coherence": 0.9, "signal": 0.85, "density": 0.8},
    "execution": {"state": 0.9, "change": 0.85, "completion": 1.0, "impact": 0.8},
    "uncertainty": 0.15
  },
  "reasoning": "Learned token refresh, implemented successfully"
}
EOF
empirica postflight-submit < postflight.json

Read the full file on GitHub · 208 lines

Changes

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.

  1. 4d ago First seen · 208 lines · 1,717 tokens per session scan A c3457d44280b

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository EmpiricaAI/empirica (245 stars, last pushed today), licensed MIT. It adds 1,717 tokens to every session, about $0.0086 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.