Borrowing it
Nothing to install: this file belongs to kezd088/100x-skill-tiktok. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kezd088/100x-skill-tiktok/master/AGENTS.mdgit clone --depth 1 https://github.com/kezd088/100x-skill-tiktokWrote 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/instructions/kezd088/100x-skill-tiktok/agents-md)<a href="https://agentmods.dev/instructions/kezd088/100x-skill-tiktok/agents-md"><img src="https://agentmods.dev/badge/instructions/kezd088/100x-skill-tiktok/agents-md/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/instructions/kezd088/100x-skill-tiktok/agents-md"><img src="https://agentmods.dev/badge/instructions/kezd088/100x-skill-tiktok/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.02174 | $0.02174 |
| Opus 5 | $0.01087 | $0.01087 |
| Sonnet 5 | $0.00435 | $0.00435 |
| Haiku 4.5 | $0.00217 | $0.00217 |
Grade A, and why
100x-skill-tiktok AGENTS.md 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
100x-skill-tiktok · 项目协作规则
面向在这个仓库工作的 agent(Claude Code / Codex / 其他)。用户全局规则见
~/.codex/AGENTS.md,那份文件管身份、沟通、授权、安全这些通用规则,不在这里重复。 本文件只写这个仓库专属、长期有效的建造契约:七件套结构、ajv 强制、公理格式、 开源合规红线、不代笔编方法论。
0 · 真源顺序
新会话进这个仓库,先按这个顺序读,不要跳步:
- 本文件 —— 长期规则,回答"该怎么做"
- 具体 skill 内部的七件套文档 —— 回答"这个 skill 自己的判据是什么"
1 · 仓库定位与写权限边界
三层架构里的第 2 层,通用能力件,上游是私有数据底座(语料、知识原子),下游是产品项目:
第1层 · 私有数据底座 (语料、知识原子,不进这个仓)
↓ requires_data 声明引用,不复制内容
第2层 · 100x-skill-tiktok ← 本仓 · 框架公开
↓ registry 钉版本
第3层 · 产品项目 (实际业务落地)
SKILL.md 是框架,atoms 是数据。前者公开,后者收费。
- 本仓是自包含的,写操作仅限本仓库。 不依赖外部仓库的写权限,所有产出均在当前工作区内完成
- 数据集依赖写在
metadata.json的requires_data字段(如["corpus.labeled_transcripts", "taxonomy.hat_copy"]),只声明 id,不复制内容 - 这是公开仓:真实客户语料、真实 transcript、真实账号名/产品名、飞书链接、Base token、API key、客户裁定的品类词典,一律不进仓——具体红线见 §5
2 · 每个 skill 固定七件套
skills/ 全平级,无分类子目录、无编号;100x- 前缀是命名空间,防止装进 ~/.claude/skills/(平铺目录)时撞名。每个 skill 目录内部固定这七个文件/目录,不精简、不新增替代结构:
| 文件/目录 | 作用 |
|---|---|
SKILL.md |
入口,Claude Code / Codex 靠这个路由。frontmatter 的 description 必须嵌用户会说的中英文触发词原话——这是 skill 被自动挑中的唯一机制,分类元数据不进这里 |
metadata.json |
结构化元数据:作者、版本、requires_data、validation(ajv 和手写代码的分工说明) |
axioms.md |
硬约束:每条公理 = 一句话 + 可机器验证断言 + 出处 + 反例作废条件,格式见 §4 |
workflow.md |
生成/判断的具体流程阶段 |
sources.md |
结论来源追溯,如实披露规则来源与本次原创内容 |
schema.json |
输出契约,JSON Schema draft-07,ajv 编译执行 |
evals/ |
只放合成样例,真实语料一条都不许进 |
3 · 校验分层:ajv 强制,手写代码只补结构层管不到的部分
- 结构层约束(
required/additionalProperties/enum/pattern这类 JSON Schema 已经能表达的东西)一律用ajv编译执行schema.json,不允许手写代码重新实现 - 跨条目/跨字段约束(JSON Schema draft-07 表达不了的部分,例如引用完整性、证据必须是原文逐字子串、5A 阶段覆盖率)才用
scripts/validate.js里的手写代码补,两层各自的职责必须写清楚在metadata.json.validation字段里,不能含糊 - 每个 skill 的
node scripts/validate.js --selftest必须能跑,且带回归用例(反例应该 FAIL 就必须真的 FAIL)
4 · axioms.md 公理格式(四要素,缺一不可)
每条公理照这个格式写,参考仓库里已建成 skill 的 axioms.md:
- 一句话 —— ≤30 字,脚本量得过的摘要
- 可机器验证断言 —— 明确写清楚哪部分
schema.json/ajv 能管、哪部分管不住需要scripts/validate.js补,两者都要点名 - 出处 —— 具体方法论文献或标准;如果是本次新定义的规则,必须如实标注"本次原创"
- 反例(作废条件) —— 什么样的输出会让这条公理判 FAIL,最好对应
--selftest里的一条回归用例
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 · 106 lines · 2,174 tokens per session scan A 8b771a3d9284
100x-skill-tiktok AGENTS.md is an instructions file published in the GitHub repository kezd088/100x-skill-tiktok (8 stars, last pushed 13d ago), licensed MIT. It adds 2,174 tokens to every session, about $0.0109 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 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.