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/solidkeyab/logan/cursorrulesgit clone --depth 1 https://github.com/SolidKeyAB/loganWhat 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 | $0.00544 | $0.00544 |
| Opus 5 | $0.00272 | $0.00272 |
| Sonnet 5 | $0.00109 | $0.00109 |
| Haiku 4.5 | $0.00054 | $0.00054 |
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 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.
What it actually says
LOGAN — Log Analyzer (Cursor Agent Instructions)
LOGAN is an Electron log analysis tool running locally. You can interact with the user through LOGAN's Chat panel.
MCP Integration
The MCP server is configured in .mcp.json. If MCP tools are available, use:
logan_status— Check if a file is open before doing anythinglogan_send_message— Send a chat message to the user in LOGANlogan_wait_for_message— Wait for user reply (blocks up to 120s)logan_get_messages— Fetch chat historylogan_search— Search the open log filelogan_get_lines— Read specific lineslogan_navigate— Jump viewer to a linelogan_analyze— Run full analysis
Chat Loop
logan_send_message("Hello!")
loop:
response = logan_wait_for_message(timeout=120)
if response.timeout: continue
if "goodbye" in response.message: break
logan_send_message(your_reply)
HTTP Fallback (if MCP unavailable)
API base: http://127.0.0.1:19532
| Action | Method | Endpoint | Body |
|---|---|---|---|
| Status | GET | /api/status | — |
| Send message | POST | /api/agent-message | {"message": "text"} |
| Poll messages | GET | /api/messages?since=TS | — |
| Search | POST | /api/search | {"pattern": "ERROR", "maxResults": 50} |
| Get lines | GET | /api/lines?start=0&count=10 | — |
| Navigate | POST | /api/navigate | {"line": 123} |
| Analyze | POST | /api/analyze | — |
| Filter | POST | /api/filter | {"pattern": "ERROR"} |
| Clear filter | POST | /api/clear-filter | — |
Always check /api/status first. Poll /api/messages?since=<timestamp_ms> every 2-3 seconds for chat.
Project Structure
src/main/— Electron main process, IPC handlers, API serversrc/renderer/— Single-file renderer (~7000+ lines), UI logicsrc/mcp-server/— MCP server (stdio), bridges to HTTP APIsrc/preload/— IPC bridge for rendererdocs/AGENT_CHAT_GUIDE.md— Full agent integration guide with examples
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.
- yesterday First seen · 54 lines · 544 tokens per session scan A 0e3b0da220df
cursorrules is a cursor rule published in the GitHub repository SolidKeyAB/logan (4 stars, last pushed 4d ago), licensed MIT. It adds 544 tokens to every session, about $0.0027 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 2026-08-31.
Other cursor rules, from other repositories
macos-system-integration
Use proper service management for background agents.
performance-optimization
// Use weak/unowned references appropriately class ViewController: UIViewController { private var timer: Timer?
webkit-browser
Cursor rule "webkit-browser" from duckduckgo/apple-browsers, covering webkit & browser development guidelines, webview configuration, basic webview setup, user scripts management and tab management.
maestro-device-selection
Maestro tests can run on either iPhone or iPad simulators based on tags in the test YAML files. This allows you to test iPad-specific UI layouts and features while maintaining a single test suite.
privacy-security
Cursor rule "privacy-security" from duckduckgo/apple-browsers, covering privacy & security guidelines, core principles, privacy by design, secure storage and data handling.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.