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/altaidevorg/rules-for-ai/session__session___basesessionservice_git clone --depth 1 https://github.com/altaidevorg/rules-for-aiWrote 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/altaidevorg/rules-for-ai/session__session___basesessionservice_)<a href="https://agentmods.dev/rules/altaidevorg/rules-for-ai/session__session___basesessionservice_"><img src="https://agentmods.dev/badge/rules/altaidevorg/rules-for-ai/session__session___basesessionservice_.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 | $0.00020 | $0.03799 |
| Opus 5 | $0.00010 | $0.01899 |
| Sonnet 5 | $0.00004 | $0.00760 |
| Haiku 4.5 | $0.00002 | $0.00380 |
Grade A, and why
session__session___basesessionservice_ 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 5d 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 — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chapter 3: Session (Session / BaseSessionService)
In the previous chapter, we explored the Agent abstraction, the core entity that processes user requests. However, conversations are rarely single-turn interactions. How does an agent remember what was said before? How does it maintain information specific to this conversation across multiple turns? This is where the Session and BaseSessionService come into play.
Motivation and Use Case
Imagine a chatbot helping users book flights.
- User: "I want to fly from London to New York."
- Agent: "Okay, London to New York. When would you like to travel?"
- User: "Sometime next week."
- Agent: "Got it. Any preferred airline?"
For the agent to ask relevant follow-up questions, it needs to remember:
- The sequence of messages exchanged (the conversation history).
- Key pieces of information extracted or inferred during the conversation (the origin, destination, and rough travel dates).
The Session object provides the mechanism to store this information. It encapsulates the conversation history and associated state, making interactions stateful. The BaseSessionService defines how these sessions are created, retrieved, updated, and stored.
Central Use Case: A user starts a chat with a travel agent bot. The application, using a Runner, creates a new Session via a BaseSessionService implementation (e.g., InMemorySessionService for testing or DatabaseSessionService for persistence). As the user interacts ("Book a flight"), the Runner retrieves the session, appends the user's message as an Event, invokes the agent, receives the agent's response Events, and appends those events to the session via the service. If the agent extracts information (like destination="New York"), it updates the session's State via an EventAction, which is persisted by the BaseSessionService when the event is appended. In the next turn, the agent can access this history and state to continue the booking process contextually.
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.
- 5d ago First seen · 274 lines · 20 tokens per session scan A 262b3ebe1043
session__session___basesessionservice_ is a cursor rule published in the GitHub repository altaidevorg/rules-for-ai (2 stars, last pushed 1y ago), licensed MIT. It adds 20 tokens to every session and 3,799 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 2026-08-31.
Other cursor rules, from other repositories
mempalace-recall-always
Always-on MemPalace recall — search the palace before answering about past work, people, projects, or prior decisions.
dreamd-recall
Recall lessons, decisions, and prior context from the .agent/ memory daemon. Use when starting work in a project that has a .agent/ folder, when the user references a past decision, or when you are about to make a choice that has a documented prior.
session-memory
Use at conversation wrap-up or when the user explicitly indicates end-of-session — capture residual lessons not captured in-flight.
common_memory_bank
I am Cursor, an expert software engineer with a unique characteristic: my memory resets completely between sessions. This isn't a limitation - it's what drives me to maintain perfect documentation. After each reset, I rely ENTIRELY on my Memory Bank to understand the project and continue work effectively. I MUST read…
context-recorder-system
Context Recorder System (记录员系统) - 模块化索引文件.
self-improving-obsidian-llm-wiki
LLM Wiki OS operating rules.