safe-refactor
Performs behavior-preserving refactors with a tight verify loop.
Skill by X-McKay
Chalk Labs
Need help deploying safe-refactor?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/x-mckay-safe-refactor
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/safe-refactor
What's inside
- Skill name
safe-refactor- Description
- Performs behavior-preserving refactors with a tight verify loop. Use when an agent restructures code without intending to change behavior.
- License
- Apache-2.0
- Instructions
- 17 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Safe Refactor Refactors must not change observable behavior. 1. Establish a green baseline: run the relevant tests before touching anything. If they are red, stop and report — do not refactor on a broken base. 2. Make one small, mechanical change at a time (rename, extract, inline). Keep each step independently revertible. 3. Re-run the targeted tests after each step. If a step goes red, revert it. 4. Treat the objective as the compatibility boundary. Remove obsolete APIs when the objective calls for a clean break; otherwise keep public behavior stable. If `avoidPublicApiChanges` is set, treat exported symbols as frozen. 5. Keep the diff minimal and reviewable; do not reformat unrelated code. Report the before/after test status and the list of mechanical steps taken.
From X-McKay/bakudo, Apache-2.0.
More from X-McKay/bakudo
- 0.524score
bakudo-maintenance
X-McKay
Maintains and validates the Bakudo repository.
SkillBFreshness: BClaude Code +9 - 0.519score
codebase-navigation
X-McKay
Efficiently maps an unfamiliar repository before making changes.
SkillBFreshness: BClaude Code +9 - 0.494score
test-selection
X-McKay
Selects the smallest relevant test set for a code change.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 10
- Last commit (this folder)
- Aug 17, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/X-McKay/bakudo
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from X-McKay
- 0.524score
bakudo-maintenance
X-McKay
Maintains and validates the Bakudo repository.
SkillBFreshness: BClaude Code +9 - 0.519score
codebase-navigation
X-McKay
Efficiently maps an unfamiliar repository before making changes.
SkillBFreshness: BClaude Code +9 - 0.494score
test-selection
X-McKay
Selects the smallest relevant test set for a code change.
SkillBFreshness: BClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get safe-refactor running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
safe-refactor skill. Agent Mart. https://agentmart.dev/skills/x-mckay-safe-refactor (last updated 2026-10-24)