ai-slop-cleaner · diff
git:20261109.6bc87c4 to git:20261111.b60b44b
1 added, 1 removed. Audit A to A.
What this update changes in the checks
No check changed: every fixed check gives the same answer before and after this update.
A tripped check is a label, not a verdict: read the matched text and the lines below. This week's updates that newly trip a check.
---
name: ai-slop-cleaner
description: "[oh-my-agy] Bounded anti-slop cleanup/refactor/deslop workflow: lock behavior with tests, plan, classify fallbacks, then dead-code, duplication, naming/error-handling, and test passes. Use when code is bloated, repetitive, over-abstracted, or AI-generated, or the user asks for cleanup/deslop."
---
# AI Slop Cleaner Task Card
Use this bounded helper for cleanup/refactor/deslop work, not as a competing top-level
workflow. Shared operating invariants live in the oh-my-agy rules; this card defines
scope, smell taxonomy, passes, and evidence.
## When to use and inputs
Use when working code is bloated, noisy, repetitive, over-abstracted, or AI-generated;
the user requests cleanup/refactor/deslop; or a follow-up left duplicate/dead code,
weak boundaries, missing tests, fallback-like paths, or wrappers. Inputs are the requested
feature/files and behavior to preserve. A file list scope is valid; keep the pass bounded
to it. Limit the pass to the calling task's changed files unless broader cleanup was requested.
- Supports `--review` for a read-only reviewer pass (separated from the writer pass) and delegates targeted post-edit simplification to the `code-simplifier` subagent when appropriate.
+ Supports `--review` for a read-only reviewer pass (separated from the writer pass) and delegates targeted post-edit simplification to the `executor` subagent (in simplification pass mode) when appropriate.
## Before editing
1. **Lock behavior with regression tests first**: identify behavior to preserve, run/add the narrowest targeted tests, and cover both primary and preserved compatibility/fail-safe fallback paths.
2. **Create a cleanup plan before code**: list scope and smells, include fallback findings/classifications/escalation, and order safest/highest-signal fixes first.
3. **Inventory fallback-like code** in scope: quick hacks, temporary workaround, temporary fallback, just bypass, just skip, fallback if it fails, swallowed errors, silent defaults, broad compatibility shims, and duplicate alternate execution paths.
4. Classify each fallback: **Masking fallback slop** hides evidence, bypasses the contract, suppresses validation, swallows failures, silently defaults, or adds untested paths; **Grounded compatibility/fail-safe fallback** is narrow at an external/version/fail-safe boundary, documents rationale, preserves failure evidence, and tests primary plus fallback.
5. Prefer root-cause repair, deletion, boundary repair, or explicit failure behavior. For broad/ambiguous/cross-layer/architectural findings, invoke `$ralplan` for consensus resolution; when already inside ralplan, ultragoal, team, or another oh-my-agy workflow, do not spawn a nested `$ralplan`—attach the finding to the active handoff.
## Smell taxonomy and passes
Classify before changing:
- **Fallback-like code**: masking fallbacks, workaround branches, bypasses, swallowed errors, silent defaults, broad shims, alternate paths.
- **Duplication**: repeated logic, copy-paste branches, redundant helpers.
- **Dead code**: unused/unreachable code, stale flags, debug leftovers.
- **Needless abstraction**: pass-through wrappers, speculative indirection, single-use layers.
- **Boundary violations**: hidden coupling, leaky responsibilities, wrong-layer imports/side effects.
- **Missing or junk tests**: behavior not locked, edge cases uncovered, or AI-generated junk tests (source-text greps, prose pinning, fixed sleeps, `.only`/`.skip` leftovers, tautological self-compares, weak `>= 0` lower bounds).
- **UI/design slop**: context-sensitive signals, not absolute bans; preserve intentional brand, design-system, accessibility, or product-context exceptions. Challenge Korean body text at 11-12px (generally 14px or larger); gratuitous box shadows; repetitive eyebrow + title + description + paragraph stacks and generic emoji badges; default AI blue/purple such as `#3B82F6`; reflexive 3-column or 4-column grids; and extreme gradients unless justified by context.
Resolve the fallback-like code resolution gate first, then one smell at a time:
**Pass 1: Dead code deletion**; **Pass 2: Duplicate removal**; **Pass 3: Naming/error
handling cleanup**; **Pass 4: Test reinforcement & junk-test pruning**. Re-run targeted verification after
each pass and avoid unrelated refactors. Prefer deletion/existing utilities; no new
abstractions or dependencies unless explicitly required.
### Pass 4: Test Slop Classification (`R / F / C / D`) & Mutation Proof
1. Run `sh <plugin>/hooks/run.sh check-test-junk <path...>` to flag regex-detectable junk-test smells (`source-grep`, `prose-pin`, `fixed-sleep`, `focused`, `skipped`, `self-compare`, `lower-bound`; suppress false positives with `// check-test-junk: ignore`).
2. Evaluate every touched test against the **4-Question Authoring Gate**: (1) What user-visible bug breaks this? (2) Does it call real production code? (3) Would a harmless internal refactor break it? (4) Did a non-redundant assertion fail before passing?
3. Classify each test as **`R`** (Real-behavior keeper), **`F`** (Weak/flaky -> strengthen in place), **`C`** (Redundant duplicate -> consolidate), or **`D`** (Junk -> delete), using the **2×2 Candidate-vs-Keeper Mutation Proof** before deleting/consolidating:
- Mutate the production code path: if **Candidate FAILS + Keeper FAILS** -> redundant (`C`, consolidate/delete); if **Candidate FAILS + Keeper PASSES** -> unique coverage (`R`, keep); if **Candidate PASSES** -> dead/tautological (`D`, delete).
- **Retention bar**: never delete a test that is the sole cover for a real bug mode unless replaced in the same change.
## Evidence/output contract
Report:
```text
AI SLOP CLEANUP REPORT
Scope: [files/feature]
Behavior Lock: [targeted tests added/run]
Cleanup Plan: [bounded smells/order]
Fallback Findings: [finding -> masking fallback slop | grounded compatibility/fail-safe fallback -> escalation]
UI/Design Findings: [none/N/A or signal -> action/defer -> intentional rationale]
Passes Completed: [resolution gate; Passes 1-4]
Quality Gates: Regression tests, Lint, Typecheck, Tests, Static/security scan (PASS/FAIL/N/A)
Changed Files: [path -> simplification]
Remaining Risks: [none or deferred item]
```
Include changed files, simplifications, fallback classifications/escalation status,
tests/diagnostics/build checks run, UI findings when relevant, and deferred risks. Keep
writer/reviewer separation for cleanup plans and approvals.
## Exit condition
Stop when the requested scope has behavior-lock evidence, each selected smell pass is
complete or explicitly deferred with rationale, verification is reported, and no
unrelated files or temporary artifacts remain. Never present an unverified cleanup as
complete; escalate a real architectural blocker rather than masking it.