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/savagelysubtle/BIG-BRAIN-Memory-BankWrote 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/savagelysubtle/big-brain-memory-bank/190-evaluation-metrics-system)<a href="https://agentmods.dev/rules/savagelysubtle/big-brain-memory-bank/190-evaluation-metrics-system"><img src="https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/190-evaluation-metrics-system/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/savagelysubtle/big-brain-memory-bank/190-evaluation-metrics-system"><img src="https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/190-evaluation-metrics-system.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 | $0.05390 |
| Opus 5 | $0.00000 | $0.02695 |
| Sonnet 5 | $0.00000 | $0.01078 |
| Haiku 4.5 | $0.00000 | $0.00539 |
Grade A, and why
190-evaluation-metrics-system 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 10d 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 — 759 lines — stays where its author put it; the contents beside it link to each section on GitHub.
description: WHEN evaluating design solutions APPLY standardized metrics for objective assessment globs: ["/*.md", "/*.mdc"] alwaysApply: true
TL;DR: The Evaluation Metrics System provides standardized criteria and measurement approaches for objectively assessing design solutions across different dimensions and design types.
1.0.0
1. **Performance Metrics**
- Response time (average, percentile, worst-case)
- Throughput (operations per unit time)
- Resource utilization (CPU, memory, network, storage)
- Scalability factors (linear, sub-linear, super-linear)
- Latency profiles (by operation type)
2. **Reliability Metrics**
- Availability (percentage uptime)
- Mean time between failures (MTBF)
- Mean time to recovery (MTTR)
- Failure rate (by component, by operation)
- Fault tolerance (degradation characteristics)
3. **Security Metrics**
- Attack surface measurement
- Vulnerability density
- Security control coverage
- Authentication strength
- Authorization granularity
- Data protection level
4. **Maintainability Metrics**
- Structural complexity
- Coupling measure
- Cohesion measure
- Documentation completeness
- Testing coverage
- Modification impact scope
5. **Usability Metrics**
- Task completion rate
- Time on task
- Error rate
- Satisfaction score
- Learnability measure
- Accessibility compliance
6. **Scalability Metrics**
- Resource scaling ratio
- Cost scaling factor
- Performance degradation curve
- Bottleneck identification
- Capacity limits
These attribute metrics provide multi-dimensional quality assessment.
1. **Cost Metrics**
- Development effort estimation
- Time-to-completion projection
- Resource requirements
- Licensing and third-party costs
- Operational cost model
2. **Complexity Metrics**
- Implementation complexity score
- Technology diversity measure
- Component interaction complexity
- Learning curve steepness
- Special expertise requirements
3. **Risk Metrics**
- Technical risk assessment
- Schedule risk factors
- Resource risk evaluation
- Dependency risk analysis
- Unknown factors estimation
4. **Integration Metrics**
- System integration effort
- Interface complexity
- Backward compatibility measure
- Forward compatibility provision
- Deployment complexity
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.
- 10d ago First seen · 759 lines · 0 tokens per session scan A e81641ac0c0c
190-evaluation-metrics-system is a cursor rule published in the GitHub repository savagelysubtle/BIG-BRAIN-Memory-Bank (5 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,390 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
web
Web build conventions (separate from native and RN JS).
components
Component patterns and UI conventions.
git
Git workflow and commit conventions.
verification-before-completion
Require fresh, scope-appropriate evidence before any completion claim. Distinguishes implemented, locally verified, repository-green, PR-green, deployed, and observed-stable states.
_project
Project-wide conventions and developer environment context (RN monorepo, no-Mac dev).
full-stack-ship-discipline
Require frontend changes and their DB/RPC/RLS/storage/secret dependencies to ship and be remotely verified together. Apply when implementing code that reads or writes backend state. Do not apply to plan- or present-then-stop audits; production data mutation still requires confirmation.