Flux desloppify

Flux Desloppify

Codebase quality scanner and fix orchestrator powered by desloppify.

Role: quality assessor, iterative fixer Goal: raise strict score to target (default 95) through systematic improvements

Session Phase Tracking

On entry, set the session phase:

PLUGIN_ROOT="${DROID_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT:-$(git rev-parse --show-toplevel 2>/dev/null || pwd)}}"
[ ! -d "$PLUGIN_ROOT/scripts" ] && PLUGIN_ROOT=$(ls -td ~/.claude/plugins/cache/nairon-flux/flux/*/ 2>/dev/null | head -1)
FLUXCTL="${PLUGIN_ROOT}/scripts/fluxctl"
$FLUXCTL session-phase set desloppify

On completion, reset:

$FLUXCTL session-phase set idle

What It Does

Combines mechanical detection (dead code, duplication, complexity) with subjective LLM review (naming, abstractions, module boundaries). Works through prioritized fix loop until target score reached.

Tier	Fix Type	Examples
T1	Auto-fixable	Unused imports, debug logs
T2	Quick manual	Unused vars, dead exports
T3	Needs judgment	Near-dupes, single_use abstractions
T4	Major refactor	God components, mixed concerns

Score is weighted (T4 = 4× T1). Strict score penalizes both open and wontfix.

Input

Full request: $ARGUMENTS

Accepts:

• No arguments → full workflow (scan → fix loop)
• scan → scan only, show score
• status → current score and progress
• next → next priority fix
• plan → prioritized markdown plan
• --path <dir> → scan specific directory (default: .)
• --target <N> → target strict score (default: 95)

Examples:

• /flux:desloppify — full improvement workflow
• /flux:desloppify scan --path src/ — scan src only
• /flux:desloppify status — check current score
• /flux:desloppify next --tier 2 — next T2 fix

Workflow

Phase 1: Setup

1. Check if desloppify is installed:

   which desloppify || pip install --upgrade "desloppify[full]"
   

2. Install the Claude skill (provides workflow guidance):

   desloppify update-skill claude
   

Phase 2: Initial Scan

Run full scan on target path:

desloppify scan --path .

Parse output for:

• Current strict score
• Issue counts by tier
• Top priority findings

Phase 3: Fix Loop

Repeat until target score reached or no more fixable issues:

1. Get next issue:

   desloppify next
   

2. Understand the issue: Read the file, understand context

3. Fix it properly: Make the code genuinely better

   • Don't game the score
   • Large refactors are fine if needed
   • Small fixes are also valuable

4. Resolve:

   desloppify resolve fixed <pattern>
   

5. Re-scan periodically to refresh findings:

   desloppify scan --path .
   

Phase 4: Report

When target reached or session ending:

• Show final score
• Summary of fixes applied
• Remaining issues by tier

Commands Reference

Command	Description
scan [--path <dir>]	Run all detectors, update state
status	Score + per-tier progress
next [--tier N]	Highest-priority open finding
resolve <status> <pattern>	Mark: fixed, wontfix, false_positive
fix <fixer> [--dry-run]	Auto-fix mechanical issues
plan	Prioritized markdown plan
tree	Annotated codebase tree
show <pattern>	Findings by file/detector/ID

Guardrails

Quality Over Speed

• Fix things properly, not superficially
• Large refactors are fine if that's what it takes
• Don't suppress warnings to game the score

Transparency

• Show the user what's being fixed and why
• Explain trade-offs for judgment calls (T3/T4)
• Don't auto-resolve without user consent for T3+

Scope

• Stay focused on the scan path
• Don't modify files outside the scanned directory
• Respect existing code style and conventions

Target Score Guide

Score	Quality Level
<70	Needs significant work
70-84	Functional but rough
85-94	Good, minor issues
95-97	Clean, well-maintained
98+	Beautiful, engineer-approved

Default target: 95 — achievable for most codebases with focused effort.

State

Desloppify maintains state in .desloppify/:

• state.json — findings, resolutions, scores
• config.json — project settings
• scorecard.png — badge for README

State persists across sessions, so improvements accumulate.

---

Update Check (End of Command)

ALWAYS run at the very end of command execution:

PLUGIN_ROOT="${DROID_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT:-$(git rev-parse --show-toplevel 2>/dev/null || pwd)}}"
[ -z "$PLUGIN_ROOT" ] && PLUGIN_ROOT=$(ls -td ~/.claude/plugins/cache/nairon-flux/flux/*/ 2>/dev/null | head -1)
UPDATE_JSON=$("$PLUGIN_ROOT/scripts/version-check.sh" 2>/dev/null || echo '{"update_available":false}')
UPDATE_AVAILABLE=$(echo "$UPDATE_JSON" | jq -r '.update_available')
LOCAL_VER=$(echo "$UPDATE_JSON" | jq -r '.local_version')
REMOTE_VER=$(echo "$UPDATE_JSON" | jq -r '.remote_version')

If update available, append to output:

---
Flux update available: v${LOCAL_VER} → v${REMOTE_VER}
Update Flux from the same source you installed it from, then restart your agent session.
---