302-agent-advanced-patterns

Guidance for coding agents on handling several files, syntax-aware refactoring, parallel work, and performance improvements.

In plain words
What is it for?
Use it for multi-file edits, renaming functions across a codebase, running independent analyses in parallel, batching work, and profiling before optimization.
Why use it?
It provides patterns for making related changes safely and efficiently, including rolling back a group of edits if tests fail.

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-agent-advanced-patterns
Clone the repo
git clone --depth 1 https://github.com/hamzaamjad/cursor-rules
Per session 6 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 304 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 $0.00006 $0.00304
Opus 5 $0.00003 $0.00152
Sonnet 5 $0.00001 $0.00061
Haiku 4.5 $0.00001 $0.00030

Measured 2d ago against content hash e39d640c8840, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

302-agent-advanced-patterns 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-agent-advanced-patterns.mdc · 53 lines

What it actually says

Advanced Agent Patterns

Multi-File Operations

# Atomic multi-file changes
changes = {
    'src/api.py': [...edits...],
    'tests/test_api.py': [...edits...],
    'docs/api.md': [...edits...]
}

with atomic_operation():
    for path, edits in changes.items():
        apply_edits(path, edits)
    run_tests()  # Rollback all if fails

AST-Based Refactoring

# Safe function rename across codebase
ast_tree = parse_codebase(['*.py'])
references = find_all_references('old_function')
for ref in references:
    edit_block(ref.file, ref.line, 'new_function')

Parallel Processing

Pattern Use Case Max Concurrent
Read-only analysis Search/lint CPU count
File writes Independent files 4-8
Test execution Unit tests CPU count
Git operations Commits 1 (serial)

Performance Optimization

  • Batch similar operations
  • Cache file reads
  • Use incremental parsing
  • Profile before optimizing
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 · 53 lines · 6 tokens per session scan A e39d640c8840

Subscribe to this mod's changes

302-agent-advanced-patterns is a cursor rule published in the GitHub repository hamzaamjad/cursor-rules (2 stars, last pushed 1y ago), licensed MIT. It adds 6 tokens to every session and 304 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.