Borrowing it
Nothing to install: this file belongs to m3taz-ahmed/ai-globals. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/m3taz-ahmed/ai-globals/main/.windsurfrulesgit clone --depth 1 https://github.com/m3taz-ahmed/ai-globalsWrote 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/m3taz-ahmed/ai-globals/windsurfrules)<a href="https://agentmods.dev/rules/m3taz-ahmed/ai-globals/windsurfrules"><img src="https://agentmods.dev/badge/rules/m3taz-ahmed/ai-globals/windsurfrules/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/m3taz-ahmed/ai-globals/windsurfrules"><img src="https://agentmods.dev/badge/rules/m3taz-ahmed/ai-globals/windsurfrules.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 | $0.00927 | $0.00927 |
| Opus 5 | $0.00464 | $0.00464 |
| Sonnet 5 | $0.00185 | $0.00185 |
| Haiku 4.5 | $0.00093 | $0.00093 |
Grade A, and why
windsurfrules 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.
This is a copy
88% identical to aizee — 10 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
aiZee
aiZee — Global Bootloader
- Root: discovered via
AIZEE_ROOTenv orconfig.discover_root()(no hardcoded path). - Set
AIZEE_ROOTif not already set. UsePYTHONIOENCODING=utf-8on Windows. - This file is the canonical root pointer. All other OS files discover the root via
AIZEE_ROOTorconfig.discover_root()and are loaded relative to it.
Working Directory [DIR-01]
- Working directory: D:\server.ai ONLY. All edits, new files, and modifications go here.
- D:\server\aizee is READ-ONLY. Never edit files in aizee directly. It is the deployment/usage folder, updated only via the batch update script.
Cold Start
- Read
global-roles.md,global-workflow.md, andMemory.md. - Detect personas with
aizee persona detect --multiand load the returnedskills/before acting. Persona switch directive (mandatory): If the user message STARTS with a persona command —#انتحل,/انتحل,#reset,/reset,#persona,/persona,#redetect,#switch(or Arabic#شخصيات,/شخصيات,#بدّل,/بدّل,#حالة,/حالة,#مين,/مين,#معلومات,/معلومات) — strip the command token, then runaizee persona detect --multi "<remaining text>"and ADOPT the returned primary + secondary personas and load theirskills/+lords/before acting. For status commands (#حالة,/status,#مين,/معلومات) print the currently active persona set instead of acting. This makes persona adoption explicit and verifiable; never silently ignore these commands. - If the current project has
spec.md, read it before any action.
Runtime Gate
- Route every action through
runtime/kernel.py. - Use
aizee check <action> --args '{"tokens":N}'orKernel.actto validate policy + budget. - No destructive action without explicit user approval.
Context & Memory
- Detect stack from
package.json/composer.jsonand load matchingtech-stack/<pkg>-<ver>.mdonly after reading the lockfile for the exact version ([VER-01]). - If
graphify-out/graph.jsonexists, usegraphify queryorquery_graph(MCP); never raw grep. - Query Context7 MCP for external libraries/frameworks before implementation; use
aizee_mcp/aizee_server.pyfor global context. - Run
aizee memory ingestwhenrules/,tech-stack/, orworkflows/change; updateMemory.mdviaworkflows/17-memory-sync.mdafter every milestone.
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 · 52 lines · 927 tokens per session scan A 9aef01a0c008
windsurfrules is a cursor rule published in the GitHub repository m3taz-ahmed/ai-globals (5 stars, last pushed yesterday), licensed MIT. It adds 927 tokens to every session, about $0.0046 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to aizee, differing in 10 lines, and is treated as a copy.
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
A modular system for recording project context, decisions, requirements, and lessons in structured files. It divides the recorder into core, template, advanced, and edge-case modules.
self-improving-obsidian-llm-wiki
LLM Wiki OS operating rules.