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/refreshdotdev/web-eval-agentWrote 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/refreshdotdev/web-eval-agent/logging-standards)<a href="https://agentmods.dev/rules/refreshdotdev/web-eval-agent/logging-standards"><img src="https://agentmods.dev/badge/rules/refreshdotdev/web-eval-agent/logging-standards/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/refreshdotdev/web-eval-agent/logging-standards"><img src="https://agentmods.dev/badge/rules/refreshdotdev/web-eval-agent/logging-standards.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 | $0.00444 | $0.00444 |
| Opus 5.5 | $0.00178 | $0.00178 |
| Sonnet 5.5 | $0.00089 | $0.00089 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
logging-standards 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.
What it actually says
Operative Control Center Logging Standards
When working with the Operative codebase, follow these logging practices:
Core Logging Principle
- NEVER use
print()statements for logging in production code - Always use the
send_log()function from the log server module for all logs
Importing the Log Function
from webEvalAgent.src.log_server import send_log
Basic Usage Pattern
# ❌ Don't do this
print("Some message")
# ✅ Do this instead
send_log("Some message", "➡️") # Second parameter is the emoji prefix
Emoji Usage Guidelines
Use appropriate emojis as the second parameter to categorize logs:
- 🚀 - Initialization/startup
- ✅ - Successful operation
- ❌ - Error
- ⚠️ - Warning
- 🔍 - Debug information
- 🖱️ - User interactions
- 🖥️ - Console logs
- 🔗 - URL/navigation related
- ➡️ - Network request
- ⬅️ - Network response
- 📝 - Information/notes
- 🏁 - Completion/final state
If a request is not one of these, find an emoji that fits!
Benefits of the Logging System
- All logs are visible in the Operative Control Center dashboard
- Logs are organized and categorized with emojis
- Users can easily copy logs for debugging
- Logging doesn't interfere with MCP server stdout/stderr
Example
# Function that performs some operation
def perform_operation():
send_log("Starting operation", "🚀")
try:
# Do something
result = process_data()
send_log(f"Operation completed with result: {result}", "✅")
return result
except Exception as e:
send_log(f"Error during operation: {e}", "❌")
raise
Always ensure logs are meaningful and provide context that helps with debugging or understanding the system state.
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 · 66 lines · 444 tokens per session scan A 5323509de670
logging-standards is a cursor rule published in the GitHub repository refreshdotdev/web-eval-agent (1,235 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 444 tokens to every session, about $0.0018 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
debugging-troubleshooting
Cursor rule "debugging-troubleshooting" from lazylagom/context-compose-mcp, covering debugging and troubleshooting guide, general debugging strategies, logging and console output, typescript type errors and mcp server debugging.
tools
MCP tool development patterns — factory pattern, base class, callbacks, and descriptions.
debugging
Debugging guidance for the Lineai MCP Server.
chrono-mcp-standards
Chrono MCP Project Standards and Guidelines.
whygraph-codegraph
Always-on guidance for using the CodeGraph (codegraph) MCP tools. Prefer them over grep for structural questions; don't pull large explore output into context; trust their AST-parsed results.
development-guidelines
Cursor rule "development-guidelines" from lazylagom/context-compose-mcp, covering development guidelines, typescript coding standards, code quality, eslint configuration and prettier formatting.