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 endearqb/endearqb-skills --skill anti-ai-slop-swarmgit clone --depth 1 https://github.com/endearqb/endearqb-skillsWrote 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/endearqb/endearqb-skills/anti-ai-slop-swarm)<a href="https://agentmods.dev/skills/endearqb/endearqb-skills/anti-ai-slop-swarm"><img src="https://agentmods.dev/badge/skills/endearqb/endearqb-skills/anti-ai-slop-swarm/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/endearqb/endearqb-skills/anti-ai-slop-swarm"><img src="https://agentmods.dev/badge/skills/endearqb/endearqb-skills/anti-ai-slop-swarm.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 | $0.00164 | $0.03198 |
| Opus 5.5 | $0.00066 | $0.01279 |
| Sonnet 5.5 | $0.00033 | $0.00640 |
| Haiku 4.5 | $0.00016 | $0.00320 |
Grade A, and why
anti-ai-slop-swarm 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 2mo 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Anti AI Slop · Swarm 编排
环境适配
| 能力 | 有 subagent（Claude Code / Cowork） | 无 subagent（Claude.ai） |
|---|---|---|
| 审稿透镜启动 | 真并行，独立上下文 | 顺序模拟，逐个透镜读判，K=1 |
| 上下文隔离 | 子 Agent 物理隔离 | 流式读取纪律：一次只装一个透镜，判完释放 |
| 红队校验 | 独立子 Agent 不读诊断 | Orchestrator 切换视角自评，标 [self-judged] |
无 subagent 环境下隔离靠纪律近似，无法消除上下文污染；追求完整隔离建议使用 Claude Code 或 Cowork。
核心抽象：四位一体对齐
slop 类别组(A–F) ↔ 审稿透镜(audit lens) ↔ dim{编号}/ 工作区 ↔ Auditor Worker
评分定位到维度 → 维度反查到透镜 → 透镜定位到 dim → 重部署 Worker
只要这条映射成立，"红队给某维度判不合格 → 反查对应透镜的诊断 → 定向重写那部分"就自动闭环。
六个透镜固定对齐 base 技能的 slop 分类六组：
| dim | 透镜 | 对应 base 分类组 | 透镜文件 |
|---|---|---|---|
| dim01 | 事实与证据 | A（1–4） | references/lens/A-facts.md |
| dim02 | 内容膨胀 | B（5–10） | references/lens/B-bloat.md |
| dim03 | 结构模板 | C（11–16） | references/lens/C-structure.md |
| dim04 | 词汇句法 | D（17–22） | references/lens/D-diction.md |
| dim05 | 对话语气 | E（23–29） | references/lens/E-tone.md |
| dim06 | 节奏格式 | F（30–35） | references/lens/F-rhythm.md |
Agent 角色（独立子智能体）
每个角色的完整指令在 agents/ 下，是该子智能体的独立 skill 文档。部署某角色时，把对应文件作为它的系统指令。
| 角色 | 数量 | 任务 | 独立文档 |
|---|---|---|---|
| Orchestrator | 1 | 锁原文、分透镜、合并去重定级、裁决、调红队、精炼、交付 | agents/orchestrator.md |
| Auditor（审稿透镜） | 6（A–F） | 各自独立诊断一组 slop，只诊断不改写 | agents/auditor.md + 对应 lens/ |
| Fact-Verifier | 0–1 | 用工具核验事实锚点（可选） | agents/fact-verifier.md |
| Rewriter | 1 | 按统一问题清单执行修改 | agents/rewriter.md |
| Loss-Verifier（红队） | 1 | 对照原文检查信息损失/事实改动/过度去味 | agents/loss-verifier.md |
| Voice-Matcher | 0–1 | 提取作者风格卡（voice-match 模式） | agents/voice-matcher.md |
铁律：审稿者只诊断不改写。 六个审稿者各改各的必然冲突；诊断与重写分离，让重写者在一份合并后的、已解决透镜间冲突的清单上一次改完。
模式
| 模式 | 跑哪些角色 | 用途 |
|---|---|---|
audit-only |
6 Auditor + 合并 | 只出诊断报告，不改稿 |
full-deslop（默认） |
6 Auditor → Rewriter → Loss-Verifier（+精炼） | 完整诊断+重写+校验 |
surgical |
6 Auditor → Rewriter（只修高/硬失败） → Loss-Verifier | 最小修补，保结构文气 |
+fact |
任意模式叠加 Fact-Verifier | 含精确数字/时效信息，需工具核验 |
+voice |
任意模式叠加 Voice-Matcher | 用户提供作者样本，需匹配声音 |
What ships with it
14 files 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.
- agents/auditor.md 3.1 KB
- agents/fact-verifier.md 1.8 KB
- agents/loss-verifier.md 3.2 KB
- agents/orchestrator.md 5.3 KB
- agents/rewriter.md 3.9 KB
- agents/voice-matcher.md 1.7 KB
- references/issue-schema.md 4.8 KB
- references/lens/A-facts.md 1.8 KB
- references/lens/B-bloat.md 1.7 KB
- references/lens/C-structure.md 1.8 KB
- references/lens/D-diction.md 2.5 KB
- references/lens/E-tone.md 2.0 KB
- references/lens/F-rhythm.md 1.8 KB
- references/quality-gate.md 3.5 KB
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.
- 2mo ago First seen · 161 lines · 164 tokens per session scan A 886f87c5523b
anti-ai-slop-swarm is a skill published in the GitHub repository endearqb/endearqb-skills (19 stars, last pushed 2mo ago), licensed MIT. It adds 164 tokens to every session and 3,198 once invoked, about $0.0007 per session on Opus 5.5. 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.
anti-ai-slop-swarm compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| anti-ai-slop-swarmendearqb/endearqb-skills | Skill | 19 | 2mo ago | MIT | A | 164 | Claude Code, Codex |
| claude-md-improveranthropics/claude-plugins-official | Skill | 46k | today | Apache-2.0 | A | 82 | Claude Code |
| agent-platform-model-registrygoogle/skills | Skill | 23k | today | Apache-2.0 | A | 60 | Claude Code, Codex |
| gke-reliabilitygoogle/skills | Skill | 23k | today | Apache-2.0 | A | 85 | Claude Code, Codex |
| gke-workload-securitygoogle/skills | Skill | 23k | today | Apache-2.0 | A | 171 | Claude Code, Codex |
| google-cloud-solution-agentic-analytics-spark-knowledge-cataloggoogle/skills | Skill | 23k | today | Apache-2.0 | A | 132 | Claude Code, Codex |
| glance-canonical-layoutsandroid/skills | Skill | 10k | 2d ago | Apache-2.0 | A | 56 | Claude Code |