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 instructions/yzr95924/agent-html-drop/agents-mdgit clone --depth 1 https://github.com/yzr95924/agent-html-dropWrote 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/yzr95924/agent-html-drop/agents-md)<a href="https://agentmods.dev/instructions/yzr95924/agent-html-drop/agents-md"><img src="https://agentmods.dev/badge/instructions/yzr95924/agent-html-drop/agents-md.svg" alt="Measured on agentmods" 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 | $0.02067 | $0.02067 |
| Opus 5 | $0.01033 | $0.01033 |
| Sonnet 5 | $0.00413 | $0.00413 |
| Haiku 4.5 | $0.00207 | $0.00207 |
Grade A, and why
agent-html-drop AGENTS.md scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`prepare_upload` 是「curl 不能带 token」时的逃生舱:走已认证 MCP 通道签发短时 HMAC capability, How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
关键:本文件里凡
@path/to/file形式的引用(如@MEMORY/MEMORY.md),都用 Read 工具按需 读取——它们与你当前任务直接相关。不自动展开@import的 agent 尤须手动执行,否则漏上下文。
项目定位
agent-html-drop 是一个常驻 HTTP daemon:让本机 AI coding agent
通过 MCP(Streamable HTTP)把 yzr-md-to-html 等产出的自包含 HTML 推到远端 nginx server,
同时提供一个浏览器管理页(列表 / 预览 / 删除 / 复制公开 URL)与可选的浏览器侧批注。
前身是 yzr-agent-tools 仓库里的 html-mcp,2026-08 独立成单工具仓库并更名。
文档分层:本文件承载 agent 工作上下文(规约 / 命令 / 架构);用户文档(安装 / 快速上手 / 命令一览 / 局限性)见根
README.md。设计文档在docs/(design.md+tasks.md+ 决策日志)。
仓库规约
- 测试绝不能触碰真实的服务配置(
~/.config/agent-html-drop/——线上 daemon 的 config.toml / token 就在那里)。tests/conftest.py的 autouse fixture 强制:snapshot 真实配置目录的 mtime,重定向paths.*到 tmp,测试结束后断言未变。 - Python 3.7+ 兼容。pyproject 固定
tomli>=1.1(<3.11 时)。CLI 用 stdlibargparse, 无第三方运行时依赖。禁dict[str, str]语法、walrus、match;用from typing import Dict, List, Optional。 - config TOML 必须透传未知字段(
config.py读写往返不丢用户自定义键)。 - 原子写文件。TOML 与 docroot 文件都先写
.tmp再os.replace(),永远不出现半写状态。 - 路径穿越防护:所有文件名过
^[A-Za-z0-9._-]+\.html$regex,绝不拼接未校验的用户输入进路径。
- 跨会话需持久化的"为什么 / 边界规则"写入根目录
MEMORY/(MEMORY.md是索引),禁写 agent 私有 memory——私有路径不随仓迁移 / 不进 git / 多 agent 各写各的会分裂成 N 份。- 完整 memory(设计决策 / 工作流约束)→
MEMORY/<slug>.md,带 frontmatter 三件套:name(=文件 slug) +description(≤200 字符事实摘要) +metadata.type(user|feedback|project|reference) - 短 memory(一句话事实)→ 直接写
MEMORY.md索引行,不单独建文件
- 完整 memory(设计决策 / 工作流约束)→
常用命令
# 容器化(2026-08-02 起为唯一种部署模式;详见 docs/design.md §15)。
# daemon 自服务 /files/*、nginx 退化为纯反代;TLS 在边缘 nginx 终结,容器内纯 HTTP。
docker compose up -d --build # 首次自动种 config + token(持久化在 ./data/)
docker compose exec agent-html-drop agent-html-drop token show # 取 token(exec 不走 ENTRYPOINT,用 wrapper)
bash scripts/docker-smoke.sh # 容器冒烟(build→/api/health→/files→token,需 docker)
# 测试 — 需要 pytest + pytest-cov 自装(pip install --user pytest pytest-cov)。
# pyproject.toml 的 [tool.pytest.ini_options].pythonpath 已含 src/,
# 不需要 `pip install -e .` 也能 import agent_html_drop。
pytest
pytest tests/test_cli.py -v # 单文件
pytest --cov=agent_html_drop # 带覆盖率
# CLI 自身
agent-html-drop init # 初始化 ~/.config/agent-html-drop/,生成 bearer token
agent-html-drop serve # 前台启动 (Ctrl+C 停);生产建议 tmux / systemd 用户单元
agent-html-drop token show # 打印 token,配到 agent MCP config
agent-html-drop nginx-config # 打印 nginx 反代片段到 stdout
agent-html-drop nginx-config --write # 写到 ~/.config/agent-html-drop/nginx.conf.example
agent-html-drop status # config / token / docroot 状态
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 · 113 lines · 2,067 tokens per session scan A 6add693bb8f7
agent-html-drop AGENTS.md is an instructions file published in the GitHub repository yzr95924/agent-html-drop (0 stars, last pushed 22d ago), licensed MIT. It adds 2,067 tokens to every session, about $0.0103 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.