Ross ROSS = Recommend OSS · open-source software intelligence for agents

peteromallet/desloppify

Agent harness to make your slop code well-engineered and beautiful. observed · 2026-08-28

github.com/peteromallet/desloppify · homepage · Python · NOASSERTION (other) observed · 2026-08-28

Health v2 · maintenance only

69/100

  • Activity 82
  • Release rhythm 83
  • Longevity 14

Flags: no_license

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: 2
  • age_days: 203
  • days_rel: 112
  • days_push: 112
  • n_releases_24m: 10

Full methodology

Adoption not part of the score

3034 stars · 235 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Desloppify is a multi-language codebase health scanner and technical debt tracker designed as an agent harness for AI coding agents. It combines mechanical detection (dead code, duplication, complexity) with LLM-based subjective review, driving a prioritized fix loop with a gaming-resistant quality score.

Use cases

  • improve codebase quality with an AI coding agent
  • scan a project for dead code and duplication
  • track and reduce technical debt over multiple sessions
  • generate a code quality scorecard badge for a README
  • get a prioritized refactoring plan for a repository
  • detect overly complex code across 29 languages

When to choose

  • you use an AI coding agent (Claude Code, Cursor, Codex, Copilot) and want it to systematically improve code quality
  • you want a quantified, gaming-resistant code health score with persistent state across sessions
  • your project is in TypeScript, Python, Go, Rust, C++, C#, Dart, or GDScript and you want deep analysis

When to avoid

  • you need a traditional CI linter with deterministic, non-LLM-only rules
  • your language is only supported by the generic tree-sitter fallback and you need deep analysis
  • you cannot run Python 3.11+ locally

Facets

cli-tool · maturity active

linter developer-tools agent-framework developer-tools programming-languages cli python cross-platform code-quality technical-debt static-analysis refactoring ai-coding-agent agent-harness code-review automation

2 sources

Member repositories

RepositoryRoleHealth v2
peteromallet/desloppifymain69

For agents

markdown · JSON · MCP: product_card(name="peteromallet/desloppify")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem