Refactor SafelySAFE

Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: refactor-safely
description: Plan and execute safe refactoring using dependency analysis
---

## Refactor Safely

Plan a refactor from the dependency graph and apply renames from a preview.

### Steps

1. Call `refactor_tool` with `mode="suggest"` for refactoring candidates, or `mode="dead_code"` for unreferenced code.
2. For a rename, call `refactor_tool` with `mode="rename"`, `old_name` and `new_name`. Check the returned edit list before applying.
3. Call `apply_refactor_tool` with the returned `refactor_id` to apply the rename.
4. Before a large refactor, call `get_impact_radius_tool` and `get_affected_flows_tool` to see the dependents and critical paths involved.
5. Call `find_large_functions_tool` to find functions worth splitting.
6. After the change, call `detect_changes_tool` to confirm the impact matches the plan.

## Token Efficiency Rules
- Call `get_minimal_context_tool(task="<your task>")` before any other graph tool.
- Pass `detail_level="minimal"` wherever a tool accepts it. Use "standard" only when minimal is not enough.
- Prefer a targeted `query_graph_tool` call over a broad listing call.
- Budget: about five tool calls and 800 tokens of graph output per task.
- Read the implementation and its tests before changing code. The graph narrows scope; it does not replace the source.

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.