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/eventgit clone --depth 1 https://github.com/altaidevorg/rules-for-aiWhat 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 | $0.03564 |
| Opus 5 | $0.00000 | $0.01782 |
| Sonnet 5 | $0.00000 | $0.00713 |
| Haiku 4.5 | $0.00000 | $0.00356 |
Grade A, and why
event 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 2d 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 — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chapter 5: Event
In the previous chapter, we explored how the State object manages the dynamic context within a conversation, tracking changes via deltas. But how are these changes, along with the actual messages and actions, recorded chronologically? This chapter introduces the Event object, the fundamental unit representing a single interaction step within a Session.
Motivation and Use Case
A simple list of text messages isn't sufficient to fully capture a complex agent interaction. We need a richer structure to represent:
- Who said or did something (user or a specific agent)?
- What was the content (text, but also structured data like function calls/responses, or even references to binary artifacts)?
- What actions were associated with this step (e.g., updating the State, transferring control to another agent)?
- What metadata provides context (when did it happen, which agent invocation generated it, does it belong to a specific sub-conversation branch)?
The Event object provides this structured representation. It serves as the immutable log entry for every significant occurrence within a conversation, forming the history stored in Session.events. This detailed history is crucial for providing context to the LLM, enabling multi-turn dialogue, debugging agent behavior, and evaluating performance.
Central Use Case: A user asks our travel agent bot, "Book a flight to Paris for next Tuesday."
- The Runner receives this input and creates an
Event(author='user',content=...). This event is added to the Session. - The Agent (BaseAgent / LlmAgent) processes this. The underlying BaseLlmFlow might yield an
Eventrepresenting the LLM's decision to call a flight search tool (author='travel_agent',content=...FunctionCall...). This event is added to the session. - The
search_flightsTool (BaseTool) executes and returns results. The flow generates anEventcontaining the results (author='search_flights',content=...FunctionResponse...) and possibly updates the state (actions.state_delta={'found_flights': [...]}). This event is added. - The flow sends the results back to the LLM, which generates the final response. The flow yields one or more
Eventobjects containing the text parts of the response (author='travel_agent',content=...Part(text=...)). These are added. Each step generates a distinctEvent, collectively forming a detailed, replayable history of the interaction.
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.
- 2d ago First seen · 245 lines · 0 tokens per session scan A d5885a13fef4
event is a cursor rule published in the GitHub repository altaidevorg/rules-for-ai (2 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,564 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
cuopt-skill-evolution
Trigger skill evolution — after solving non-trivial problems, propose skill updates.
cursorrules
See CLAUDE.md for full context. Quick rules.
moyu
当检测到过度工程模式时自动激活：修改用户未要求的代码、创建不必要的抽象层、 添加未要求的注释/文档/测试、引入不必要的依赖、重写整个文件而非最小编辑、 diff 超出请求范围。用户说"太多了"、"只改 X"、"简单点"时触发。 Activates on over-engineering: modifying unrequested code, unnecessary abstractions, unsolicited comments/docs/tests, unrequested dependencies, full file rewrites, scope-exceeding diffs. Triggers on "too…
cursorrules
This repository contains a structured skill library for AI-assisted product development. Skills are in skills//SKILL.md. Read the relevant SKILL.md before generating any artifact.
cursorrules
AgentAnycast is a decentralized P2P runtime for the A2A (Agent-to-Agent) protocol.
homunculus
Homunculus self-evolving AI assistant. Use when user asks about evolution cycles, goal trees, system status, instincts, or skills. Provides routing to detailed evolution workflows.