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 agentmods add skills/telagod/code-abyss/reducing-aigc-detectionnpx skills add telagod/code-abyss --skill reducing-aigc-detectiongit clone --depth 1 https://github.com/telagod/code-abyssWhat 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 | $0.00062 | $0.02355 |
| Opus 5 | $0.00031 | $0.01177 |
| Sonnet 5 | $0.00012 | $0.00471 |
| Haiku 4.5 | $0.00006 | $0.00235 |
Grade A, and why
reducing-aigc-detection 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 3d 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
降AIGC · reducing-aigc-detection
检测器追的是统计均匀性，反检测的本质是重新注入人类写作天然的 variance 和 imperfection。
何时使用
| 场景 | 使用 | 说明 |
|---|---|---|
| AIGC 检测报告显示高于红线 | YES | 核心场景 |
| 论文提交前预防性降 AI | YES | 不需要检测报告 |
| 已有 AI 辅助写作的论文需要人性化 | YES | 最佳实践 |
| 纯人工写作但误判率高 | YES | 可针对性微调 |
| 想批量处理多份文件 | NO | 每篇需要定制化处理 |
核心原理
检测器三板斧
| 指标 | 含义 | AI 文本特征 | 人类文本特征 |
|---|---|---|---|
| Perplexity（困惑度） | 文本可预测性 | 极低（<30） | 中高（60-120） |
| Burstiness（突发性） | 句长变化幅度 | 极低，句长均匀 | 高，长短交替 |
| Token 概率分布 | high-prob token 占比 | >85% | <70% |
平台差异
| 平台 | 特殊机制 | 关键应对 |
|---|---|---|
| 维普 | 章节加权（摘要 1.8x，引言/结论 1.5x）；拼接预警（风格断层 +10-15%） | 优先改摘要；全文风格一致 |
| 知网 | 3.0+ 分析论证深度曲线；4.0 标注"结构工整度过高" | 制造浅→深螺旋节奏 |
| Turnitin | 2025.8 可识别 humanizer 工具痕迹 | 不用洗稿工具，手动改写 |
执行流程
Phase 0: 侦察
- 读取检测报告 PDF（如有），提取各章节 AIGC 占比
- 如无报告，通读全文预判高风险段落
- 按 AIGC 率 x 章节权重 排序，确定改写优先级
优先级 = AIGC率 × 章节字数 × 平台权重系数
Phase 1: 分级定策
| AIGC 率 | 策略 | 改动幅度 |
|---|---|---|
| >80% | 整段重写 | 保留核心论点，彻底换表达 |
| 40-80% | 重点改写 | 换骨架、注入个人经验、打碎并列 |
| 20-40% | 局部手术 | 替换 AI 特征词、打断过渡链、加短句 |
| <20% | 微调或不动 | 仅修复明显 AI 模板词 |
Phase 2: 改写执行
改写层级（按效果排序）
第一层：结构层（降 60-70%，最高优先）
- 消灭「N个方面：第一…第二…第三…」并列模板
- 打破「背景→分析→结论」标准三段论
- 制造论证深度不均匀：核心论点厚写，次要一笔带过
- 长短句交替：穿插 5-10 字短句与 30-40 字长句
- 加入自我修正轨迹：「最初以为…后来发现…」
第二层：词汇层（降 10-15%，配合第一层）
中文 AI 高频触发词黑名单（必须替换或删除）：
值得注意的是 / 综上所述 / 不可否认 / 首先…其次…最后
研究表明 / 结果显示 / 此外 / 总之 / 不仅…而且
主要体现在N个方面 / 具有重要意义 / 发挥着重要作用
在…方面 / 与此同时 / 一方面…另一方面
英文 AI 高频触发词黑名单：
delve(s) / furthermore / moreover / it is important to note
comprehensive / multifaceted / nuanced / landscape / underscores
in conclusion / this report hopes to / integrates...with
The X section explains/introduces/presents/summarizes (mechanical parallelism)
替换策略：不是换同义词，是换句式。「研究表明X」→ 引具体作者年份样本量。
第三层：内容注入（最难被检测）
- 加入个人研究细节、田野观察、实验意外
- 引用对立观点的具体文献
- 补充具体数据、数字、表格
- 增加口语化学术表达碎片
技术执行注意事项
docx 编辑策略：
| 段落类型 | 编辑方式 | 理由 |
|---|---|---|
| 无脚注/无特殊格式 | replace_full_para() — 设 Run 0 新文本，清空其余 |
安全快速 |
| 含脚注引用 [N] | Run 级替换 — 仅改非 superscript runs | 保留脚注 |
| 含 bold/italic 段中格式 | Run 级替换或 XML 层编辑 | 保留格式标记 |
| 含图表引用 | 仅改文字 runs，不动图表 XML | 防止引用断裂 |
What ships with it
2 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.
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.
- 3d ago First seen · 197 lines · 62 tokens per session scan A fc9bf6ad95f9
reducing-aigc-detection is a skill published in the GitHub repository telagod/code-abyss (239 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 2,355 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 2026-08-30.
Other skills, from other repositories
codexkit-api-design-reviewer
Review REST and GraphQL API designs for consistency, usability, and best practices. Covers naming conventions, versioning strategy, error format, pagination, authentication patterns, and breaking change detection. Use when reviewing API specs, designing new APIs, or auditing existing endpoints.
codexkit-change-management-plan
Build change management plans using ADKAR and Kotter's 8-Step framework. Covers stakeholder readiness, communication plans, training schedules, resistance management, and adoption metrics. Use when rolling out new systems, reorganizations, or process changes that affect people.
codexkit-crisis-communication
Draft crisis communication packages including holding statements, stakeholder updates, Q&A documents, and internal briefs. Follows ICS (Incident Command System) communication principles. Use during PR crises, data breaches, product recalls, or any event requiring rapid coordinated messaging.
codexkit-interview-guide-builder
Build structured behavioral interview guides using the STAR method. Map job competencies to interview questions, provide scoring rubrics (1–5), and include follow-up probes and red/green flag indicators. Use when preparing for hiring interviews or standardizing interview practices.
codexkit-legal-due-diligence
Conduct structured legal due diligence for M&A, joint ventures, or investment transactions. Cover all 9 workstreams — Corporate, Contracts, IP, Litigation, Regulatory, Employment, Tax, Environmental, and Data Privacy. Produce a risk matrix with deal-breaker flags and closing conditions. Use when evaluating a target or…
codexkit-a-b-test-planner
Design rigorous A/B test plans with hypothesis, sample size calculation, Minimum Detectable Effect (MDE), randomization strategy, and decision rules. Includes guardrail metrics and rollout playbook. Use when planning product experiments, conversion optimization, or data-driven feature decisions.