refactoring

A step-by-step workflow for safely changing existing code without changing what it should do. It uses project context, dependency information, focused code reading, and tests.

In plain words
What is it for?
Use it to extract logic such as authentication code, understand the files it affects, make the refactor, and verify it with tests.
Why use it?
It reduces the risk of missing related code or breaking behavior during a refactor. Running the test suite provides a check after the change.

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/arrayo/smart-context-mcp/refactoring
Clone the repo
git clone --depth 1 https://github.com/Arrayo/smart-context-mcp
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 179 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 $0.00000 $0.00179
Opus 5 $0.00000 $0.00089
Sonnet 5 $0.00000 $0.00036
Haiku 4.5 $0.00000 $0.00018

Measured yesterday against content hash d8ed209009d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

refactoring 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 yesterday.

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.

tools/devctx/agent-rules/profiles-compact/refactoring.mdc · 20 lines

What it actually says

Refactoring Workflow

1. smart_turn(start, userPrompt='Extract auth logic')
2. smart_context(entryFile=<target>, detail=balanced, include=['content','graph'])
   → Dependency graph + file content in one call
3. smart_read(mode=symbol, symbol=<function to refactor>)
   → Only if smart_context didn't include the target
4. [refactor code]
5. smart_shell('npm test') → verify
6. smart_turn(end, summary='...')

Key: smart_context(entryFile=...) gives you the dependency graph and relevant content. Only call smart_read(symbol) for functions not covered. Always verify tests after refactoring.

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. yesterday First seen · 20 lines · 0 tokens per session scan A d8ed209009d5

Subscribe to this mod's changes

refactoring is a cursor rule published in the GitHub repository Arrayo/smart-context-mcp (4 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 179 tokens. 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.