continuous-improvement

A guide for improving an AI assistant's project rules as repeated coding patterns, bugs, review comments, and new practices appear.

In plain words
What is it for?
Use it to analyze recurring code patterns and errors, add examples from the codebase, handle new edge cases, and remove outdated guidance.
Why use it?
It provides criteria for when rules should be added or updated, so useful lessons are recorded instead of repeatedly rediscovered.

Cursor rule

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/steipete/agent-rules/continuous-improvement
Clone the repo
git clone --depth 1 https://github.com/steipete/agent-rules
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,469 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00016 $0.01469
Opus 5 $0.00008 $0.00734
Sonnet 5 $0.00003 $0.00294
Haiku 4.5 $0.00002 $0.00147

Measured yesterday against content hash cf1f5cb667b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

continuous-improvement 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 yesterday.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

project-rules/continuous-improvement.mdc · 296 lines

How it starts

The opening of the file, as written. The whole thing — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Continuous Improvement Guide for AI Development Rules

This guide provides a systematic approach for continuously improving AI assistant rules based on emerging patterns, best practices, and lessons learned during development.

Rule Improvement Triggers

When to Create or Update Rules

Create New Rules When:

  • A new technology/pattern is used in 3+ files
  • Common bugs could be prevented by a rule
  • Code reviews repeatedly mention the same feedback
  • New security or performance patterns emerge
  • A complex task requires consistent approach

Update Existing Rules When:

  • Better examples exist in the codebase
  • Additional edge cases are discovered
  • Related rules have been updated
  • Implementation details have changed
  • User feedback indicates confusion

Analysis Process

1. Pattern Recognition

Monitor your codebase for repeated patterns:

// Example: If you see this pattern repeatedly:
const data = await prisma.user.findMany({
  select: { id: true, email: true },
  where: { status: 'ACTIVE' }
});

// Consider documenting:
// - Standard select fields
// - Common where conditions  
// - Performance optimization patterns

2. Error Pattern Analysis

Track common mistakes and their solutions:

Common Error: "Connection timeout"
Root Cause: Missing strategic delay after service startup
Solution: Add 5-10 second delay after launching services
Rule Update: Add timing guidelines to automation rules

3. Best Practice Evolution

Document emerging best practices:

## Before (Old Pattern)
- Direct DOM manipulation
- No error handling
- Synchronous operations

## After (New Pattern)  
- Use framework methods
- Comprehensive error handling
- Async/await with proper error boundaries

Rule Quality Framework

Structure Guidelines

Each rule should follow this structure:

# Rule Name

## Purpose
Brief description of what this rule achieves

## When to Apply
- Specific scenarios
- Trigger conditions
- Prerequisites

## Implementation
### Basic Pattern
```code
// Minimal working example
```

### Advanced Pattern
```code
// Complex scenarios with error handling
```

## Common Pitfalls
- Known issues
- How to avoid them

## References
- Related rules: [rule-name.md]
- External docs: [link]

Read the full file on GitHub · 296 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. yesterday First seen · 296 lines · 16 tokens per session scan A cf1f5cb667b6

Subscribe to this mod's changes

continuous-improvement is a cursor rule published in the GitHub repository steipete/agent-rules (5,696 stars, last pushed 4mo ago), licensed MIT. It adds 16 tokens to every session and 1,469 once invoked, about $0.0001 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.