tirth8205/code-review-graph

refactor-safely

Plan and execute safe refactoring using dependency analysis

First seen Jul 17, 2026

Installation

$ npx skills add tirth8205/code-review-graph --skill refactor-safely

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from tirth8205/code-review-graph.

npx skills add tirth8205/code-review-graph

Browse all from tirth8205/code-review-graph

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 31.3K
License LICENSE
Default branch main
Open issues 88
Status Active

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 1,331 B
  • docs SUMMARY.md 82 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 1,000 installs

SKILL.md

Refactor Safely

Use the knowledge graph to plan and execute refactoring with confidence.

Steps

  1. Use refactor_tool with mode="suggest" for community-driven refactoring suggestions.
  2. Use refactortool with mode="deadcode" to find unreferenced code.
  3. For renames, use refactor_tool with mode="rename" to preview all affected locations.
  4. Use applyrefactortool with the refactor_id to apply renames.
  5. After changes, run detectchangestool to verify the refactoring impact.

Safety Checks

  • Always preview before applying (rename mode gives you an edit list).
  • Check getimpactradius_tool before major refactors.
  • Use getaffectedflows_tool to ensure no critical paths are broken.
  • Run findlargefunctions_tool to identify decomposition targets.

Token Efficiency Rules

  • Start with getminimalcontext_tool(task="<your task>") before other graph tools.
  • Use detail_level="minimal" on all calls. Only escalate to "standard" when minimal is insufficient.
  • Target: complete any review/debug/refactor task in ≤5 tool calls and ≤800 total output tokens.
  • Read the implementation and its tests before changing code. The graph narrows scope; it does not replace the source.