Sponsor Suno AI Music arrow_forward
Slash Command

Elegant Code Review

Review the current working diff against the elegant-code decision ladder and propose deletions, honoring the negligence floor.

Type
Slash Command
GitHub stars
339
License
MIT
Repo last updated
Sep 24, 2026

What Elegant Code Review is

Elegant Code Review is a slash command published in the athola/claude-night-market repository on GitHub, which has about 339 stars. The repository describes itself as: “23 Claude Code plugins: TDD enforcement hooks, git/PR workflows, spec-driven development, code review, project lifecycle, fix-from-error, maintenance automation, context optimization, research, and multi-LLM delegation. 186 skills, 128 commands, 54 agents.”

A slash command is a reusable prompt saved as a markdown file and run by typing its name after a slash. In Claude Code, custom commands have been merged into skills: a file in .claude/commands/ and a skill folder in .claude/skills/ both create the same kind of command, and existing command files keep working.

Elegant Code Review gives you a repeatable way to run the same instructions without retyping them, optionally with arguments.

How to install Elegant Code Review

Claude Code

  1. Download elegant-code-review.md from the repository.
  2. Save it to ~/.claude/commands/ (all projects) or .claude/commands/ (one project). As a skill, you can instead save it as ~/.claude/skills/<name>/SKILL.md.
  3. Run it by typing / followed by its name.

Claude Cowork

  1. Turn the command into a skill: create a folder with the file saved as SKILL.md and zip it.
  2. In Customize → Skills, click +, then upload the ZIP.
  3. Run it from any task with / and the skill name.

New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.

Inside the source file

An excerpt from plugins/conserve/commands/elegant-code-review.md, shared under the repository's MIT license. Read the full file on GitHub.

Walk the current working diff against the elegant-code decision ladder. For each added hunk, name the rung that justifies it, flag any rung skipped, and propose concrete deletions. This is a per-change review. For whole-codebase cleanup, use /unbloat.

When To Use

  • After writing or generating a change, before committing.
  • When a diff feels larger than the problem it solves.
  • When a new dependency appears in a lockfile or manifest.

When NOT To Use

  • Whole-codebase dead-code sweeps: use /unbloat or /bloat-scan.
  • Throwaway scripts where review cost is near zero.

Steps

  1. Load the rubric: Skill(conserve:elegant-code).
  2. Collect the diff:
  • Default: git diff (unstaged) plus git diff --staged.
  • --staged: staged changes only.
  • --base REF: git diff REF...HEAD.
  1. For each added hunk, assign the lowest ladder rung that justifies it:
  2. Need-to-exist
  3. Builtin / stdlib
  4. Native platform
  5. Installed dependency
  6. A few lines A new dependency is the last resort, below rung 5. If one was added, confirm it with Skill(imbue:dependency-verification) and check whether an installed dependency already covered the need.
  7. Cross-check deletability with a real tool when available, treating output as candidates only:
   command -v knip >/dev/null && knip || echo "knip absent; skipping"
   command -v vulture >/dev/null && vulture . || echo "vulture absent; skipping"
  1. Apply the negligence floor before proposing any deletion. Never propose removing input validation, authorization, data-loss handling, error handling, security paths, or accessibility.
  2. Check completeness, not just excess. Flag a hunk that handles only the happy path: missing edge cases (empty, None, zero, boundary), missing negative or failure paths, or an obvious performance trap (quadratic loop, N+1 query). Minimal code that omits these is unfinished, not lean.

Output

A short table, one row per reviewed hunk:

Close with a one-line verdict: minimal and complete, trim suggested, new dependency unjustified, or incomplete: add coverage. List proposed deletions, and any missing edge, negative, or performance coverage, as concrete diffs the user approves before anything changes.

Notes

  • Read-only by default: propose, do not delete without approval.
  • Composes leyline:additive-bias-defense for the burden-of-proof verdict on each addition.

Before you install

  • Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
  • Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
  • Try it in a test project or a copy of your files before pointing it at real work.
  • Pin the version you tested, and review changes before updating.
  • Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.

FAQ

What is Elegant Code Review?

Elegant Code Review is a slash command for Claude Code and Claude Cowork from the athola/claude-night-market repository on GitHub. Review the current working diff against the elegant-code decision ladder and propose deletions, honoring the negligence floor.

How do I install Elegant Code Review in Claude Code?

Download elegant-code-review.md from the repository. Save it to ~/.claude/commands/ (all projects) or .claude/commands/ (one project). As a skill, you can instead save it as ~/.claude/skills/<name>/SKILL.md. Run it by typing / followed by its name.

Can I use Elegant Code Review in Claude Cowork?

Turn the command into a skill: create a folder with the file saved as SKILL.md and zip it. In Customize → Skills, click +, then upload the ZIP. Run it from any task with / and the skill name.

Is Elegant Code Review safe to install?

It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.

Similar resources

Browse all skills, subagents, and plugins →

Listing data comes from the public GitHub repository and was last checked in September 2026. Excerpts are © their authors and shared under MIT. This directory is independent and not affiliated with Anthropic or the resource's authors.