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.
npx skills add vibeeval/vibecosystem --skill ai-slop-cleanergit clone --depth 1 https://github.com/vibeeval/vibecosystemWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/vibeeval/vibecosystem/ai-slop-cleaner)<a href="https://agentmods.dev/skills/vibeeval/vibecosystem/ai-slop-cleaner"><img src="https://agentmods.dev/badge/skills/vibeeval/vibecosystem/ai-slop-cleaner/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/vibeeval/vibecosystem/ai-slop-cleaner"><img src="https://agentmods.dev/badge/skills/vibeeval/vibecosystem/ai-slop-cleaner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00050 | $0.03097 |
| Opus 5 | $0.00025 | $0.01548 |
| Sonnet 5 | $0.00010 | $0.00619 |
| Haiku 4.5 | $0.00005 | $0.00310 |
Grade A, and why
ai-slop-cleaner 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 421 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Slop Cleaner
AI code generation produces working code. It also produces unnecessary code alongside it. This skill removes the unnecessary parts while keeping everything that matters.
What Is "AI Slop"?
AI slop is code that:
- Works, but shouldn't exist
- Adds complexity without adding value
- Was clearly generated to pad a response rather than solve a problem
- Suggests the author wasn't thinking, just generating
Common slop categories and their signals:
| Category | Signal |
|---|---|
| Dead imports | Imported but never referenced in the file |
| Unused variables | Declared, never read |
| Commented-out code | Blocks of // old code or /* removed */ |
| Debug remnants | console.log, print(), debugger, fmt.Println |
| Obvious comments | // increment counter above count++ |
| Redundant JSDoc | @param name - the name above name: string |
| Premature abstractions | A factory that creates exactly one thing |
| One-use helpers | Private function called exactly once, trivially inlinable |
| Overly generic types | <T extends object> when T is always User |
| Over-parameterized | fn(a, b, c, d, e) where 4 params never vary |
| Unreachable branches | if (false) or if (isLoggedIn && !isLoggedIn) |
| Speculative features | Code paths for requirements that don't exist |
| Copy-paste duplication | Two blocks identical except one variable name |
| Placeholder remnants | TODO: implement, lorem ipsum, example data in prod |
The Prime Directive
Tests are sacred. Never clean test files.
Tests exist to protect behavior. Any cleanup that breaks a test reveals that the "slop" was actually load-bearing. That is good information. The test wins.
Regression-Safe Workflow (Non-Negotiable)
BEFORE ANYTHING: Run full test suite → all tests must pass (baseline)
FOR EACH PASS:
1. Identify targets for this pass category
2. Apply cleanup
3. Run tests
4. If tests pass: keep cleanup, continue
5. If tests fail: git checkout -- . (revert), skip this pass category
6. Log what was reverted and why
AFTER ALL PASSES: Run full test suite → confirm all tests still pass
Report: lines removed, files touched, passes skipped, reason for each skip
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.
- 7d ago First seen · 421 lines · 50 tokens per session scan A afaf01465972
ai-slop-cleaner is a skill published in the GitHub repository vibeeval/vibecosystem (529 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 3,097 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
review-loop
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…
scrutinize
Ultrathink principal-engineer review gate. Runs a Validate-Identify-Improve-Adjust (VIIA) pass over a target - a plan awaiting approval, just-executed work, a specific file or directory, or the entire workspace - then runs an adversarial refutation layer (Phase 2.5) with cross-family judge rotation (Claude and Kimi…
anti-stub-scan
Scan a diff for stub patterns and TODO markers.
bug-hunt
Proactive bug-hunting workflow. Assesses codebase risk through complexity, coverage, and structural analysis, then spawns focused investigators that write reproducing tests to validate suspected bugs. Thoroughness over speed. Advisory only — produces findings and proposes tickets; does not implement fixes.
gs-review
Pre-landing PR review - gstack staff-engineer code review army. CARL TRIGGERS: review the code, audit this branch, check this PR, find bugs, code review, review my changes. SOURCE: garrytan/gstack/review, integrated as gs-review on 2026-05-29.
observability-audit
Audit code for observability gaps — debug logs left in, errors caught without being logged, missing context on log entries, untracked slow operations. Uses the app's existing observability tooling exclusively.