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/brunogama/ios-cursor-rulesWrote 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/brunogama/ios-cursor-rules/knowledge-management-rule)<a href="https://agentmods.dev/rules/brunogama/ios-cursor-rules/knowledge-management-rule"><img src="https://agentmods.dev/badge/rules/brunogama/ios-cursor-rules/knowledge-management-rule/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/brunogama/ios-cursor-rules/knowledge-management-rule"><img src="https://agentmods.dev/badge/rules/brunogama/ios-cursor-rules/knowledge-management-rule.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 | $0.02695 | $0.02695 |
| Opus 5.5 | $0.01078 | $0.01078 |
| Sonnet 5.5 | $0.00539 | $0.00539 |
| Haiku 4.5 | $0.00269 | $0.00269 |
Grade A, and why
knowledge-management-rule 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 1mo 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 — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Management System
Rule for capturing, organizing, refining, and applying knowledge throughout the project lifecycle.
Learning refinement filters
- type: event pattern: "learning_create"
- type: event pattern: "learning_update"
- type: file_change pattern: ".cursor/learnings/*.md"
- type: command pattern: "knowledge"
Actionable insights filters
- type: command pattern: "insight"
- type: event pattern: "implementation_complete"
- type: event pattern: "task_complete"
- type: event pattern: "code_review"
- type: file_change pattern: "src/*"
actions:
SECTION 1: KNOWLEDGE CAPTURE
-
type: react conditions:
- pattern: "learn add|learning create" action: |
Create a new learning entry
I'll create a structured learning document with:
- Unique ID (format: LEARN-YYYY-MM-DD-NN)
- Title and short description
- Detailed description of the learning (including context related to SOLID, TDD, SRP, Calisthenics, resilience if applicable)
- Relevant code files (using
Sources/,Tests/paths), tasks (managed by development_workflow_system), specifications (managed by specification_management), and documents - Date of capture
- Keywords for easy retrieval
The learning will be stored in
.cursor/learnings/and indexed in.cursor/LEARNINGS.md -
type: react conditions:
- pattern: "document add|document create|document detect" action: |
Register a document in the knowledge base
I'll register the document by:
- Storing a copy in
.cursor/docs/if it's not already there - Creating a learning entry about this document
- Adding the document to the documents index
- Extracting key information from the document
- Creating cross-references to related content including specifications (managed by specification_management)
This ensures all project documentation is centrally tracked and discoverable.
-
type: react event: "conversation_insight" action: |
Automatically capture important insights from our conversations
When I identify valuable insights in our conversation, I'll:
- Create a learning entry with the insight
- Generate a unique ID for the learning
- Categorize and tag the insight appropriately
- Add context and relevant connections to tasks (managed by development_workflow_system)
- Index the insight for future reference
This ensures important information isn't lost.
-
type: react event: "file_change" conditions:
- pattern: ".cursor/docs/.*" action: |
Automatically process new documents added to docs directory
When a new document is added to
.cursor/docs/, I'll:- Extract key information from the document
- Create a learning entry linked to this document
- Update the documents index
- Identify related content including specifications (managed by specification_management)
- Generate appropriate metadata
This ensures all documentation is properly integrated into the knowledge base.
SECTION 2: KNOWLEDGE ORGANIZATION & REFINEMENT
-
type: react conditions:
- pattern: "learn categorize|learning categorize" action: |
Categorize and organize learnings
I'll organize all learnings into meaningful categories:
- Analyze all learning content to identify topics and themes
- Categorize learnings into domains like:
- Architecture, Performance, Security, DevOps
- UX, API, Database, Testing
- Frontend, Backend, Mobile, Tooling
- Process, Bugs, Documentation
- Create category files in
.cursor/learning_categories/ - Generate a categories index with links to all categorized learnings
- Identify uncategorized learnings for further review
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.
- 1mo ago First seen · 347 lines · 2,695 tokens per session scan A 5ec9896c234c
knowledge-management-rule is a cursor rule published in the GitHub repository brunogama/ios-cursor-rules (75 stars, last pushed 1y ago), licensed MIT. It adds 2,695 tokens to every session, about $0.0108 per session on Opus 5.5. 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
swiftui
Rules for IcySky, a SwiftUI project for a bluesky client.
202-swift-standards-detailed
A detailed set of coding standards for Swift 6.2 and Apple platforms from iOS 18 through iOS 26.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.