Borrowing it
Nothing to install: this file belongs to TianyiDataScience/humanize. 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/TianyiDataScience/humanize/main/AGENTS.mdgit clone --depth 1 https://github.com/TianyiDataScience/humanizeWrote 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/tianyidatascience/humanize/agents-md)<a href="https://agentmods.dev/instructions/tianyidatascience/humanize/agents-md"><img src="https://agentmods.dev/badge/instructions/tianyidatascience/humanize/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/tianyidatascience/humanize/agents-md"><img src="https://agentmods.dev/badge/instructions/tianyidatascience/humanize/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 | $0.00569 | $0.00569 |
| Opus 5.5 | $0.00228 | $0.00228 |
| Sonnet 5.5 | $0.00114 | $0.00114 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
humanize 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 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.
What it actually says
Agent 使用说明
这个仓库是一个通用的中文文案 humanize skill，不绑定单一 agent。
CoPaw / OpenClaw 这类 agent 的使用方式本质相同：读取 SKILL.md，在 skill 目录里执行 CLI。仓库里的 scripts/install_to_copaw.py 只是把文件同步到当前已知的 CoPaw workspace 路径，不代表 CoPaw 使用另一套协议。
适用环境：
- CoPaw
- OpenClaw
- Claude Code
- Hermes
- 任何能读取
SKILL.md并执行本地 shell 命令的 agent
规范入口
默认只调用这个命令：
python3 humanize.py --text "{完整用户请求}" --output-root ./runs
如果在 skill 目录外执行，先进入仓库根目录：
cd /path/to/humanize
python3 humanize.py --text "{完整用户请求}" --output-root ./runs
不要这样做
- 不要手写
challenger.txt来绕过官方流程。 - 不要自己主观挑 winner。
- 不要传
--mode rewrite，rewrite 会自动从--text或--original推断。 - 不要把用户的长
原文丢掉，只传一个总结后的--task。 - 不要在命令成功后再附加一版手工改写。
输出规则
如果命令输出：
=== HUMANIZE_FINAL_RESPONSE_BEGIN ===
...
=== HUMANIZE_FINAL_RESPONSE_END ===
最终回复用户时，只返回两个 marker 中间的 markdown。
生成模型
默认优先使用可检测到的宿主 active model；当前仓库已内置 CoPaw active model 桥接。
如果当前 agent 没有提供可检测的 active model，可以配置本地 OpenAI-compatible endpoint：
export HUMANIZE_GENERATION_BACKEND=local
export HUMANIZE_LLM_BASE_URL=http://127.0.0.1:54841/v1
export HUMANIZE_LLM_MODEL=<your-local-model-id>
如果你用的是 Ollama 上的 thinking 模型，建议再加：
export HUMANIZE_LLM_REASONING_EFFORT=none
如果在 Apple 芯片机器上想避免 scorer 首次走 MPS 带来的等待，也可以固定：
export HUMANIZE_SCORER_DEVICE=cpu
没有生成模型时，系统会降级到 heuristic-only，常见模板化文案仍可跑完整流程。
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 · 75 lines · 569 tokens per session scan A 89fda31373b5
humanize AGENTS.md is an instructions file published in the GitHub repository TianyiDataScience/humanize (96 stars, last pushed 6mo ago), licensed MIT. It adds 569 tokens to every session, about $0.0023 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.
humanize AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| humanize AGENTS.mdTianyiDataScience/humanize | Instructions file | 96 | 6mo ago | MIT | A | 569 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |