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 | $0.00082 | $0.01599 |
| Sonnet 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 12d 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.
- 12d 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 9d ago), licensed MIT. It adds 164 tokens to every session and 3,198 once invoked, about $0.0008 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
taiyi-evolve
A workflow skill that compares the implemented code with the frozen design after development and testing. It records architecture changes and proposes updates to DESIGN.md, the document describing the intended system structure.
reply-to-pr-threads
Draft, confirm, and post replies to GitHub PR review threads. Handles per-category reply formatting, re-fetches thread resolution state so auto-resolved threads are skipped, and posts via GraphQL. Use when the user asks to "reply to PR threads", "post PR thread replies", or "draft PR reply messages".
answer-reviewer-questions
For each reviewer question on a PR, recall implementation reasoning and compose a raw answer. Use when the user asks to "answer reviewer questions", "draft answers to PR questions", or "explain reviewer questions".
evaluate-findings
Critically assess external feedback (code reviews, AI reviewers, PR comments) and decide which suggestions to apply using adversarial verification. Use when the user asks to "evaluate findings", "assess review comments", "triage review feedback", "evaluate review output", or "filter false positives".
create-project-skills
Scans an existing codebase and generates project-specific skills that capture inferred conventions such as naming, file organization, framework usage, data access, error handling, and testing style. Writes into the project's chosen skill directory (e.g., .claude/skills/, .agents/skills/, or a custom path). Use when…
retrospective-audit
Stage B of /prflow:retrospective-weekly: given a most-recent-first subset of one recurring pattern's occurrence-PR context bundles (bounded by auditbundlecap), re-derive the root cause and return one JSON object carrying a ranked findings array (one to three sub-patterns) — no edits, no worktree. Invoked as a subagent…