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/savagelysubtle/big-brain-memory-bank/command-executiongit clone --depth 1 https://github.com/savagelysubtle/BIG-BRAIN-Memory-BankWhat 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 | $0.00702 | $0.00702 |
| Opus 5 | $0.00351 | $0.00351 |
| Sonnet 5 | $0.00140 | $0.00140 |
| Haiku 4.5 | $0.00070 | $0.00070 |
Grade A, and why
command-execution scanned grade A with 0 findings against 26 rules in 11 categories โ prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency โ 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
100% identical to command-execution โ 0 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 โ 130 lines โ stays where its author put it; the contents beside it link to each section on GitHub.
COMMAND EXECUTION PROTOCOL
TL;DR: Execute commands ONE AT A TIME. Document each command's purpose, the command itself, and its result (success OR failure).
๐ซ PROHIBITED PATTERNS
Never use these command patterns:
โ COMMAND CHAINING - DO NOT USE:
cd todo-app && npm install
โ IMPLICIT CHAINING (NESTED DIRS) - DO NOT USE:
mkdir -p src/components/TodoList
โ MULTIPLE FILE OPERATIONS - DO NOT USE:
touch index.js style.css app.js
โ MULTIPLE PACKAGE INSTALLS - DO NOT USE:
npm install react react-dom react-router-dom
cd todo-app && npm install # DON'T do this - will crash terminal
โ CORRECT PATTERNS
โ CORRECT: Separate navigation and installation
cd todo-app
npm install
โ CORRECT: Using tool-based directory creation
Instead of mkdir commands, prefer using built-in tools:
Use list_dir tool to check existing directories Use edit_file tool to create files in new directories
For example, creating a component structure:
- Use relative paths when working with tools
- Create parent directories first, then child directories
- Create files within directories as neededdc. The edit prioritizes the built-in tools while maintaining the principle of creating one directory at a time to avoid terminal crashes.
โ CORRECT: One file at a time
touch index.js
touch style.css
touch app.js
โ CORRECT: One package at a time
npm install react
npm install react-dom
npm install react-router-dom
๐ COMMAND DOCUMENTATION FORMAT
Document EVERY command using this format:
### Command: [Brief Description]
Purpose: [Explain what this command will do]
```bash
[actual command]
Result: [What happened after execution] Next step: [What follows this command]
## ๐ FAILED COMMAND DOCUMENTATION FORMAT
When a command fails, document it using this format:
Command: [Brief Description]
Purpose: [Explain what this command will do]
[attempted command]
Result: FAILED Error message: [Error details]
Alternative Approach
[alternative command]
Resolution: [How the issue was resolved] Next step: [What follows this command]
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 ยท 130 lines ยท 702 tokens per session scan A d1eb1ade69ee
command-execution is a cursor rule published in the GitHub repository savagelysubtle/BIG-BRAIN-Memory-Bank (5 stars, last pushed 1y ago), licensed MIT. It adds 702 tokens to every session, about $0.0035 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to command-execution, differing in 0 lines, and is treated as a copy.
Other cursor rules, from other repositories
skill-workflows
Capabilities catalog for cursor-kenji skills. Routes requests to the right skill or bundled workflow. Always-on routing index โ the agent consults this to pick between individual skills and bundled workflows.
composer-2.5-execution
Guard execution of approved plan/burndown work: forbid reward hacking and feature deletion; require checkpoints, context discipline, safe terminal use, and fresh verification. Apply to approved plan-.md, complete-everything, or burndown-full runs; binding for any implementation model.
verification-before-completion
Require fresh, scope-appropriate evidence before any completion claim. Distinguishes implemented, locally verified, repository-green, PR-green, deployed, and observed-stable states.
composer-coding-excellence
Coding craft โ surgical edits, convention matching, no scope creep, no slop comments, no fabricated APIs.
composer-core
Always-on builder spine โ continue the app, demoable slice, Build loop, Run/Wired handoff, ask only on high confusion weight.
clarify-first
Infer-and-act by default โ ask only on high confusion weight, after inspecting, with a decision-linked question.