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.
git clone --depth 1 https://github.com/tecnomanu/pampaWrote 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/tecnomanu/pampa/file-guard)<a href="https://agentmods.dev/rules/tecnomanu/pampa/file-guard"><img src="https://agentmods.dev/badge/rules/tecnomanu/pampa/file-guard.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 5.1 | $0.00250 | $0.00250 |
| Opus 5 | $0.00125 | $0.00125 |
| Sonnet 5 | $0.00050 | $0.00050 |
| Haiku 4.5 | $0.00025 | $0.00025 |
Grade A, and why
file-guard 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 7d 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.
What it actually says
File Management Guard
Before creating a file, check if it already exists. If it exists and there is no explicit instruction to overwrite, merge content instead of replacing.
Best Practices for File Operations
-
Check Existence: Always verify if a file exists before creating it.
-
Preserve Content: When a file exists, preserve important elements:
- Comments and documentation
- Existing imports
- License headers
- Configuration settings
-
Merge Strategies:
- For code files: Add new functions, classes, or methods without removing existing ones
- For configuration files: Add new settings while preserving existing ones
- For documentation: Append new information or integrate it with existing content
-
Communicate Changes: When modifying existing files, document the nature of the changes.
When to Overwrite
Only overwrite files when:
- Explicitly instructed to do so
- The file is known to be a generated file that should be recreated
- The entire purpose of the file is being changed
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.
- 7d ago First seen · 36 lines · 250 tokens per session scan A 5d0a252a7908
file-guard is a cursor rule published in the GitHub repository tecnomanu/pampa (30 stars, last pushed 11mo ago), licensed ISC. It adds 250 tokens to every session, about $0.0013 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 2026-08-30.
Other cursor rules, from other repositories
cursor-behavior-constraints
Constraints on how Cursor should behave when designing and implementing UX, UI, IA, and accessibility patterns.
design-core
Balanced always-on core of UX, UI, IA, and accessibility principles for every interaction.
enterprise-ia-patterns
Use for complex, multi-product or multi-tenant IA. Covers cross-product navigation, deep hierarchies, account/org structures, and wayfinding at scale.
ia-navigation-and-structure
Information architecture patterns for navigation, structure, and labeling.
group_what_shares_common_meaning
Methods should group only lines of code that share a common intention. Different responsibilities must be extracted into separate methods or services.
method_naming_should_reflect_intention
Method names must clearly communicate the action or intention of the method. The level of detail should correspond to the method’s position in the execution chain.