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/empiricaai/empirica/cursorrulesgit clone --depth 1 https://github.com/EmpiricaAI/empiricaWrote 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/empiricaai/empirica/cursorrules)<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>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 | $0.01717 | $0.01717 |
| Opus 5 | $0.00859 | $0.00859 |
| Sonnet 5 | $0.00343 | $0.00343 |
| Haiku 4.5 | $0.00172 | $0.00172 |
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.
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
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 · 208 lines · 1,717 tokens per session scan A c3457d44280b
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.
Other cursor rules, from other repositories
cursor-memory
Shokunin memory system: persistent context across sessions.
gps-skin-ui
/Users/theodoreaddo/.cursor/rules/gps-skin-ui.mdc.
cursorrules
🧠 Fast, zero-dependency structured knowledge base (.agent-kb/) with 2D neural graph visualizer │ & MCP server for Claude, Codex, PI, Cursor, Windsurf, Zed & Other AI coding agents.
langgraph-best-practices
Comprehensive reference for building LangGraph agent workflows including core concepts, graph construction patterns, state management, advanced patterns like Send API and Command, and production-ready code examples.
churn-prevention
When the user wants to reduce churn or build retention systems — 'cancel flow,' 'save offer,' 'dunning,' 'failed payment recovery,' 'win...
orchestrate
Apply the Workflow Orchestration methodology for complex, multi-step tasks — plan-first approach, subagent strategy, self-improvement loo...