command-execution

Command execution guidelines for isolation-focused Memory Bank.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/bia-technologies/yaxunit/command-execution
Clone the repo
git clone --depth 1 https://github.com/bia-technologies/yaxunit

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 2,228 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.02228
Opus 5 $0.00000 $0.01114
Sonnet 5 $0.00000 $0.00446
Haiku 4.5 $0.00000 $0.00223

Measured today against content hash 3f88c33ce358, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

command-execution 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 today.

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.

.cursor/rules/isolation_rules/Core/command-execution.mdc · 235 lines

How it starts

The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.

COMMAND EXECUTION SYSTEM

TL;DR: This system provides guidelines for efficient command execution, balancing clarity and token optimization through appropriate command chaining, with proper documentation of commands and results.

🔍 COMMAND EFFICIENCY WORKFLOW

graph TD
    Start["Command<br>Planning"] --> Analyze["Analyze Command<br>Requirements"]
    Analyze --> Balance["Balance Clarity<br>vs. Efficiency"]
    Balance --> Complexity{"Command<br>Complexity?"}
    
    Complexity -->|"Simple"| Single["Execute<br>Single Command"]
    Complexity -->|"Moderate"| Chain["Use Efficient<br>Command Chaining"]
    Complexity -->|"Complex"| Group["Group Into<br>Logical Steps"]
    
    Single & Chain & Group --> Verify["Verify<br>Results"]
    Verify --> Document["Document<br>Command & Result"]
    Document --> Next["Next<br>Command"]

📋 COMMAND CHAINING GUIDELINES

graph TD
    Command["Command<br>Execution"] --> ChainApprop{"Is Chaining<br>Appropriate?"}
    
    ChainApprop -->|"Yes"| ChainTypes["Chain<br>Types"]
    ChainApprop -->|"No"| SingleCmd["Use Single<br>Commands"]
    
    ChainTypes --> Sequential["Sequential Operations<br>cmd1 && cmd2"]
    ChainTypes --> Conditional["Conditional Operations<br>cmd1 || cmd2"]
    ChainTypes --> Piping["Piping<br>cmd1 | cmd2"]
    ChainTypes --> Grouping["Command Grouping<br>(cmd1; cmd2)"]
    
    Sequential & Conditional & Piping & Grouping --> Doc["Document<br>Commands & Results"]

🚦 DIRECTORY VERIFICATION WORKFLOW

graph TD
    Command["Command<br>Execution"] --> DirCheck["Check Current<br>Directory"]
    DirCheck --> ProjectRoot{"In Project<br>Root?"}
    
    ProjectRoot -->|"Yes"| Execute["Execute<br>Command"]
    ProjectRoot -->|"No"| Locate["Locate<br>Project Root"]
    
    Locate --> Found{"Project Root<br>Found?"}
    Found -->|"Yes"| Navigate["Navigate to<br>Project Root"]
    Found -->|"No"| Error["Error: Cannot<br>Find Project Root"]
    
    Navigate --> Execute
    Execute --> Verify["Verify<br>Results"]

Read the full file on GitHub · 235 lines

Changes

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.

  1. today First seen · 235 lines · 0 tokens per session scan A 3f88c33ce358

Subscribe to this mod's changes

command-execution is a cursor rule published in the GitHub repository bia-technologies/yaxunit (322 stars, last pushed 2mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,228 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 2026-09-01.