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/synaptiai/prompt-decorators/050-careful-code-modificationgit clone --depth 1 https://github.com/synaptiai/prompt-decoratorsWrote 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/synaptiai/prompt-decorators/050-careful-code-modification)<a href="https://agentmods.dev/rules/synaptiai/prompt-decorators/050-careful-code-modification"><img src="https://agentmods.dev/badge/rules/synaptiai/prompt-decorators/050-careful-code-modification.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 | $0.00356 | $0.00356 |
| Opus 5 | $0.00178 | $0.00178 |
| Sonnet 5 | $0.00071 | $0.00071 |
| Haiku 4.5 | $0.00036 | $0.00036 |
Grade A, and why
050-careful-code-modification 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 4d 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
Careful Code Modification
1.0.0
Context
- When modifying existing code in this codebase
- When fixing bugs or implementing new features
- When the codebase is fragile or has complex dependencies
Requirements
- Make surgical, precise modifications targeting only the specific issue
- Implement proper validation procedures before and after changes
- Consider the scope and potential side effects of all changes
- Ensure changes are appropriate for the sensitivity level of the codebase
- Add thorough tests for any modifications made
- Document changes clearly with comments explaining the rationale
Examples
# Fix specific calculation issue only
corrected_value = data['value'] * 1.05 # Apply 5% correction
# Return with minimal changes to data structure
result = data.copy()
result['value'] = corrected_value
return result
return new_data # Returns completely different structure
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.
- 4d ago First seen · 54 lines · 356 tokens per session scan A 0d175cc15494
050-careful-code-modification is a cursor rule published in the GitHub repository synaptiai/prompt-decorators (43 stars, last pushed yesterday), licensed Apache-2.0. It adds 356 tokens to every session, about $0.0018 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
react
React, TypeScript, and web development best practices for performance optimization.
session-distill
How to distill a long work session into ContextForge so a fresh session can resume cleanly. Invoke when the user asks to distill/hand off/checkpoint the session, when context is getting bloated and work is unfinished, or before deliberately starting a new session on the same task.
mcp-tools-readme
Keep README in sync when MCP tools change.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.