302-cursor-agent-core

A set of rules for using Cursor Agent to make codebase changes through a read, plan, edit, and verification cycle. It covers choosing edit methods, handling multi-file changes, and checking the result with tests.

In plain words
What is it for?
Use it as operating guidance for Cursor Agent when editing one file, changing many files, refactoring code, or migrating data or structure.
Why use it?
It gives the coding agent a consistent process that reduces accidental overwrites and unverified changes. The rules also describe safer patterns for renaming, refactoring, and migrations.

Cursor rule

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/hamzaamjad/cursor-rules/302-cursor-agent-core
Clone the repo
git clone --depth 1 https://github.com/hamzaamjad/cursor-rules
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 294 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original 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 $0.00008 $0.00294
Opus 5 $0.00004 $0.00147
Sonnet 5 $0.00002 $0.00059
Haiku 4.5 $0.00001 $0.00029

Measured 2d ago against content hash 1c9fc1eda833, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

302-cursor-agent-core 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 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.

rules/300-integration/302-cursor-agent-core.mdc · 47 lines

What it actually says

Cursor Agent Core

Purpose: Reliable autonomous codebase changes.

Essential Workflow

# 1. Read → 2. Plan → 3. Apply → 4. Verify
content = read_file(path)
changes = analyze_modifications(content)
apply_with_verification(path, changes)
run_terminal_cmd("pytest")

Tool Priority

Operation Primary Fallback
Surgical edit edit_block edit_file
Full rewrite write_file Manual chunks
Multi-file Batch operations Sequential

Safety Rules

  1. Always read before edit
  2. Verify after every change
  3. Rollback on validation failure
  4. Test before claiming success

Quick Patterns

  • Rename: Find all → Edit each → Verify
  • Refactor: AST analysis → Staged edits
  • Migrate: Backup → Transform → Validate

Details: @lazy_load

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. 2d ago First seen · 47 lines · 8 tokens per session scan A 1c9fc1eda833

Subscribe to this mod's changes

302-cursor-agent-core is a cursor rule published in the GitHub repository hamzaamjad/cursor-rules (2 stars, last pushed 1y ago), licensed MIT. It adds 8 tokens to every session and 294 once invoked, about $0.0000 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 2026-08-31.