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/first-fluke/fullstack-starterWrote 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/first-fluke/fullstack-starter/preferred-editing-tools)<a href="https://agentmods.dev/rules/first-fluke/fullstack-starter/preferred-editing-tools"><img src="https://agentmods.dev/badge/rules/first-fluke/fullstack-starter/preferred-editing-tools/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/first-fluke/fullstack-starter/preferred-editing-tools"><img src="https://agentmods.dev/badge/rules/first-fluke/fullstack-starter/preferred-editing-tools.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 | $0.00004 | $0.00562 |
| Opus 5.5 | $0.00002 | $0.00225 |
| Sonnet 5.5 | $0.00001 | $0.00112 |
| Haiku 4.5 | $0.00000 | $0.00056 |
Grade A, and why
preferred-editing-tools 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 1mo 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preferred File Editing Tools
Overview
This rule mandates the use of specialized agentic tools for file modifications instead of fragile shell commands. It establishes a hierarchy of tools, prioritizing semantic and structural editing over raw text manipulation.
Rules
1. No Shell-Based Editing
Strictly prohibited to use the following for editing or creating files:
echosedawkprintfcat > filename<<EOFheredocs
Why?
- Usage of shell redaction allows for escaping issues, special character mismanagement, and encoding errors.
- It often leads to corrupt files or partial writes in complex codebases.
2. Tool Priority Hierarchy
You MUST follow this priority order when selecting a tool for file modification. Always check if a higher-priority tool can accomplish the task before moving to a lower-priority one.
Priority 1: Standard Text Block Editing (Native)
Use these for simple, contiguous text replacements where structural tools are overkill or inapplicable.
replace_file_content: For replacing a single contiguous block of lines.multi_replace_file_content: For making multiple, non-contiguous edits in a single file.
Priority 2: File Creation & Overwrite (Native)
Use these for new files or when a complete rewrite is easier/necessary.
write_to_file: For creating new files or overwriting existing files (withOverwrite: true).
Priority 3: Semantic & Symbolic Editing (Serena MCP)
Use these first. These tools respect the syntax and structure of the code (LSP-based).
mcp_serena_rename_symbol: For renaming variables, functions, classes, etc. across the codebase.mcp_serena_insert_before_symbol/mcp_serena_insert_after_symbol: For inserting code relative to existing symbols (e.g., adding a method to a class).
Priority 4: Structured & Pattern-Based Editing (Serena MCP)
Use these if no specific symbol is targeted. These offer robust regex support and larger context handling.
mcp_serena_replace_content: For replacing content using powerful regex (Pythonresyntax) or literal strings.- Tip: Use regex mode with wildcards (e.g.,
start.*?end) to safely replace blocks without quoting the entire content.
- Tip: Use regex mode with wildcards (e.g.,
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.
- 1mo ago First seen · 50 lines · 4 tokens per session scan A dde704bb0653
preferred-editing-tools is a cursor rule published in the GitHub repository first-fluke/fullstack-starter (224 stars, last pushed today), licensed MIT. It adds 4 tokens to every session and 562 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-09-03.
Other cursor rules, from other repositories
cursorrules
Cursor rule "cursorrules" from CopilotKit/CopilotKit, covering instructions, additional command options and notes.
knowledge
This file explains the Knowledge Base feature and how it's implemented.
ai-collaboration
Instructions for AI agent code generation workflow.
git-conventions
Git workflow and commit conventions for AI-assisted development.
schemas
Sanity schema and Studio config conventions.
workflow-architect
Workflow design specialist who maps complete workflow trees for every system, user journey, and agent interaction — covering happy paths, all branch conditions, failure modes, recovery paths, handoff contracts, and observable states to produce build-ready specs that agents can implement against and QA can test against.