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/gargoyle92/agentify-mcp/05-session-managementgit clone --depth 1 https://github.com/gargoyle92/agentify-mcpWrote 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/gargoyle92/agentify-mcp/05-session-management)<a href="https://agentmods.dev/rules/gargoyle92/agentify-mcp/05-session-management"><img src="https://agentmods.dev/badge/rules/gargoyle92/agentify-mcp/05-session-management.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.02142 |
| Opus 5 | $0.00000 | $0.01071 |
| Sonnet 5 | $0.00000 | $0.00428 |
| Haiku 4.5 | $0.00000 | $0.00214 |
Grade A, and why
05-session-management 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 3d 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 — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.
05-Session-Management
Session Management Architecture
Session management is handled by session-manager.ts and state tracking by state-tracker.ts.
Core Responsibilities
- SessionManager: Client lifecycle, status tracking, metrics collection
- StateTracker: File system monitoring, performance metrics, project detection
CRITICAL SESSION RULES - MUST FOLLOW
✅ ALWAYS DO:
- Use SessionManager for all client operations: Never directly manipulate client objects
- Emit events for state changes: All client status changes must emit events
- Update activity timestamps: Every client interaction must update lastActivity
- Validate client existence: Always check if client exists before operations
- Implement cleanup: Regular cleanup of inactive clients and resources
❌ NEVER DO:
- Direct client manipulation: Never modify client objects outside SessionManager
- Skip event emission: Never change client state without emitting events
- Ignore session isolation: Client data must be isolated by clientId
- Forget resource cleanup: Always clean up watchers and intervals on client disconnect
- Bypass session validation: Never assume a session exists without checking
Client Registration Patterns
✅ PROPER Client Registration:
// Complete client registration with all required fields
export class SessionManager extends EventEmitter {
public registerClient(client: AgentClient): void {
// Validate required fields
if (!client.id || !client.type || !client.name) {
throw new Error('Invalid client: missing required fields');
}
// Set connection info
client.connectionInfo = {
...client.connectionInfo,
connectedAt: new Date(),
lastActivity: new Date(),
};
// Initialize metrics if not provided
client.metrics = {
requestCount: 0,
errorCount: 0,
uptime: 0,
...client.metrics,
};
this.clients.set(client.id, client);
this.emit('clientConnected', client);
this.logger.info(`Client registered: ${client.id} (${client.type})`);
// Start tracking for this client
this.stateTracker?.startTracking(client.id);
}
}
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.
- 3d ago First seen · 319 lines · 0 tokens per session scan A 3836c9b4c4da
05-session-management is a cursor rule published in the GitHub repository gargoyle92/agentify-mcp (1 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,142 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
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.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.