quality

A quality-improvement command for software projects that checks tests, coverage, performance, bundle size, code quality, and security. Test coverage measures how much of the code is exercised by automated tests; a bundle is the files shipped to a web browser.

In plain words
What is it for?
Use it to fix failing tests, add edge-case and integration tests, measure performance, reduce browser bundle size, improve type safety, and address security problems.
Why use it?
It helps find untested behavior, slow code, oversized web assets, lint and type problems, dependency vulnerabilities, and other maintenance issues.

Command for Claude Code

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 commands/sylphxai/coderag/quality
Clone the repo
git clone --depth 1 https://github.com/SylphxAI/coderag

Made for: Claude Code.

Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 869 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 $0.00015 $0.00869
Opus 5 $0.00008 $0.00434
Sonnet 5 $0.00003 $0.00174
Haiku 4.5 $0.00002 $0.00087

Measured 2d ago against content hash ab8ea52deee4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

quality 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 2d ago.

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.

.claude/commands/quality.md · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Quality Assurance

Maximize quality metrics: tests, coverage, performance, bundle size.

Scope

Testing:

  • Fix failing tests
  • Add missing tests (.test.ts for all modules)
  • Improve coverage (critical paths 100%, business logic 80%+)
  • Test edge cases
  • Test error paths
  • Integration tests
  • E2E tests (if applicable)

Benchmarking:

  • Add benchmarks (.bench.ts for critical functions)
  • Measure performance
  • Identify regressions
  • Optimize slow operations

Performance:

  • Profile hot paths
  • Optimize algorithms (reduce complexity)
  • Fix memory leaks
  • Reduce allocations
  • Cache expensive operations
  • Lazy load where possible

Bundle Size:

  • Analyze bundle composition
  • Remove unused dependencies
  • Tree-shake effectively
  • Code split strategically
  • Compress assets
  • Use dynamic imports

Code Quality:

  • Fix lint errors/warnings
  • Improve type safety (no any)
  • Reduce complexity
  • Improve maintainability
  • Follow code standards

Security:

  • Fix vulnerabilities
  • Update dependencies
  • Validate inputs
  • Sanitize outputs
  • Secure defaults

Execution

1. Test Coverage

# Run tests with coverage
npm run test:coverage

# Identify gaps
# Add tests for uncovered code
# Focus on critical paths first

Priority:

  • Critical business logic (100%)
  • Error handling (100%)
  • Edge cases (90%)
  • Happy paths (100%)
  • Integration points (80%)

2. Benchmarking

# Run benchmarks
npm run bench

# Compare against baseline
# Identify regressions
# Optimize bottlenecks

Add benchmarks for:

  • Algorithm complexity (O(n) vs O(n²))
  • Database queries
  • API calls
  • Data processing
  • Rendering (if UI)

3. Performance Profiling

# Profile application
node --inspect ...
# Or use Clinic.js, 0x, etc.

# Identify bottlenecks
# Optimize hot paths
# Measure improvements

Check:

  • CPU usage
  • Memory usage
  • I/O operations
  • Network calls
  • Rendering time

4. Bundle Analysis

# Analyze bundle
npm run build -- --analyze

# Check size
ls -lh dist/

# Identify large dependencies
# Remove unnecessary code

Read the full file on GitHub · 183 lines

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. 2d ago First seen · 183 lines · 15 tokens per session scan A ab8ea52deee4

Subscribe to this mod's changes

quality is a command published in the GitHub repository SylphxAI/coderag (12 stars, last pushed 7d ago), licensed MIT. It adds 15 tokens to every session and 869 once invoked, about $0.0001 per session on Opus 5. 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 2026-08-30.