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 DeevsDeevs/agent-system --skill anti-ai-slopgit clone --depth 1 https://github.com/DeevsDeevs/agent-systemWrote 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/deevsdeevs/agent-system/anti-ai-slop)<a href="https://agentmods.dev/skills/deevsdeevs/agent-system/anti-ai-slop"><img src="https://agentmods.dev/badge/skills/deevsdeevs/agent-system/anti-ai-slop/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/deevsdeevs/agent-system/anti-ai-slop"><img src="https://agentmods.dev/badge/skills/deevsdeevs/agent-system/anti-ai-slop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 3 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- high Rogue Agent · line 29 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- high Rogue Agent · line 61 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- high Prompt Injection · line 200 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00033 | $0.01754 |
| Opus 5 | $0.00016 | $0.00877 |
| Sonnet 5 | $0.00007 | $0.00351 |
| Haiku 4.5 | $0.00003 | $0.00175 |
Grade A, and why
anti-ai-slop 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 9d 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 — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intent
This skill reviews the diff against main and removes changes that are likely “AI slop”: unnecessary, non-idiomatic, or inconsistent additions that do not materially contribute to the intended feature/fix.
Guiding principle: keep the smallest change that accomplishes the goal, and match the local conventions of each touched file.
Scope and diff source
Operate only on changes introduced on this branch relative to main.
Determine the diff source in this order:
git diff --cached(if non-empty)git diff(if non-empty)git diff main..HEAD(fallback)
Ifmaindoes not exist locally, usegit diff master..HEAD.
Do not refactor unrelated code outside the displayed diff hunks.
Non-goals
- Do not redesign architecture, rename APIs, or move code unless required by the feature/fix in the diff.
- Do not remove meaningful domain comments that encode invariants, reasoning, constraints, or known pitfalls.
- Do not remove validation at genuine trust boundaries (I/O, parsing, network, user input, third-party callbacks).
- Do not change formatting rules; follow repository tooling and the file’s established style.
What counts as AI slop
A) Comment and documentation bloat
Remove comments/docstrings that merely narrate the code, restate names, or are inconsistent with the file’s comment density and tone.
Python (before):
def clamp(x: float, lo: float, hi: float) -> float:
# Ensure x is not less than lo and not greater than hi
if x < lo:
return lo
if x > hi:
return hi
return x
Python (after):
def clamp(x: float, lo: float, hi: float) -> float:
if x < lo:
return lo
if x > hi:
return hi
return x
B) Unnecessary defensive checks inside trusted codepaths
Remove checks that are redundant because upstream validation/types/invariants already guarantee inputs.
Rust (before):
pub fn normalize_tag(tag: &str) -> String {
if tag.is_empty() {
return String::new();
}
tag.trim().to_ascii_lowercase()
}
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 247 lines · 33 tokens per session scan A 8a545cce2d64
anti-ai-slop is a skill published in the GitHub repository DeevsDeevs/agent-system (40 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 1,754 once invoked, about $0.0002 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.
Other skills, from other repositories
omc-review
Evaluate finished work for defects, risk, and simplification before it ships.
plannotator
Reference for using the Plannotator CLI: plan review, code review, annotating files, URLs, folders, and running local apps, annotating the last assistant message, browsing archived plan decisions, and exporting or sharing Guided Reviews. Invoke when asked to use Plannotator for anything not covered by a more specific…
refactor
Guides a refactor, cleanup, or restructure with the right decomposition. Use when the user asks to refactor, simplify, extract, or modernize code.
work-with-pr
Full PR lifecycle in a fresh task-owned git worktree: implement via the ulw-loop skill with mandatory evidence-bound manual QA → reviewer-readable English PR → verification loop (CI + Cubic, where Cubic is skipped only when its quota is exhausted) → merge by default → worktree cleanup. Decomposes one task into the…
remove-ai-slops
Removes AI-generated code smells from branch changes or an explicit file list behind regression tests. Use when the user asks to clean up, deslop, or remove AI-slop patterns from recent changes.
review-work
Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.